Demonstrating AI Temperature

When you request something from ChatGPT via the API one of the options you can set is “temperature”. LLMs are a machine which predicts the next word to follow after the words that came before. But temperature being higher lets it be less predictable and not always take the most default probability. I was trying to explain this to a friend over coffee so I thought running a quick demo would be helpful.

I’ve run the same query 3 times with increasing temperatures. Starting at zero, which to my surprise still didn’t produce identical results and the second they drift they they go a different path. The highest settings didn’t return a result at all in the time limit I gave it.

Interesting it seems very very keen on the layer cake. It only shakes loose of that at high settings. But the examples at higher settings don’t actually explain recursion very well!

Personally I’d have gone with “kitkats” because the recipie for KitKats includes crushed KitKat…

Anyhow here we go…

Prompt: “Explain recursion with a cooking analogy.”

temperature=0 (deterministic)

run 1

Recursion is like following a recipe that requires you to make a smaller version of the same dish before you can complete the final dish.

Imagine you’re making a layered cake. The recipe says to first bake a smaller cake (the base layer). Once that’s done, you need to bake another smaller cake for the next layer. You keep repeating this process, baking smaller and smaller cakes until you reach the smallest size, which is just a cupcake.

Once all the smaller cakes are baked, you can start assembling them into the final layered cake. Each time you bake a smaller cake, you’re solving a smaller part of the overall problem (making the full cake). Finally, when all the smaller parts are ready, you combine them to complete the dish.

In recursion, a function calls itself with a simpler version of the original problem until it reaches a base case, just like you keep baking smaller cakes until you reach the smallest one.

run 2

Recursion is like following a recipe that requires you to make a smaller version of the same dish before you can complete the final dish.

Imagine you’re making a layered cake. The recipe says to first bake a smaller cake layer. Once that layer is done, you use it as a base to build the larger cake. If the recipe calls for multiple layers, you keep repeating the process: bake a smaller layer, then stack it, until you have the full cake.

In this analogy, each time you bake a smaller layer, you’re performing a recursive step. The final cake is built upon these smaller layers, just as a recursive function builds upon its smaller instances to reach a final solution.

run 3

Recursion is like following a recipe that requires you to make a smaller version of the same dish before you can complete the final dish.

Once all the smaller cakes are baked, you can start assembling them into the final layered cake. Each time you bake a smaller cake, you’re using the same recipe, just on a smaller scale. Finally, when all the layers are stacked, you have your complete cake.

In recursion, a function calls itself with a simpler or smaller problem until it reaches a base case, just like you keep baking smaller cakes until you reach the smallest one.

temperature=0.7 (default)

Note that these all stay the same for the first few words.

run 1

Recursion is like following a recipe that calls for the same recipe to be used multiple times. Imagine you’re making a layered cake.

1. You start by making a cake base (the first step).
2. The recipe might say, “For each layer, make another cake base.”
3. So, you make a smaller cake for the first layer (this is the recursive call).
4. Once you have enough layers, you stop making smaller cakes and start stacking them together.

In this analogy, each time you make a new cake base, you’re repeating the process, but you eventually reach a point where you stop and assemble everything into a final product. That’s how recursion works—solving a problem by breaking it down into smaller instances of the same problem until you reach a base case.

run 2

Recursion is like following a recipe that requires you to make a smaller version of a dish before you can complete the larger one.

Imagine you want to make a layered cake, but the recipe calls for you to first bake a smaller cake to use as one of the layers. You follow the same steps: mix ingredients, bake, and then once that smaller cake is ready, you use it as a layer in the larger cake.

If the recipe for the smaller cake requires yet another smaller cake, you repeat the process. Eventually, you reach a point where you can bake a single cupcake, which is simple enough to complete. Once that cupcake is done, you can build back up, using it to create the smaller cake, and then the larger cake, until your full layered cake is complete.

In this analogy, each smaller cake represents a recursive call, and the final cupcake is the base case that stops the recursion.

run 3

Recursion is like following a recipe that requires you to prepare a dish using another dish as an ingredient. For example, imagine you need to make a layered cake. The recipe starts with making a batch of cake batter, which is then baked into layers.

1. To create the layered cake, you first need to make the cake layers (this is your base case).
2. If you want to make a more complex dessert, you might need to prepare a flavored frosting, which requires you to make a basic frosting first (this is the recursive call).
3. Then, you assemble the layers with the frosting in between.

Each time you make a layer or a frosting, you’re essentially calling the same recipe process, but you’re getting closer to completing your final dish. Once all layers and frostings are done, you have your completed layered cake.

In this analogy, the recipe calls for itself at different stages, just like a recursive function calls itself until it reaches a base case.

temperature=1 (creative)

run 1

Recursion is like following a recipe that calls for the same dish to be made within itself, such as a layered cake.

1. You start by making the first layer of the cake, which may require mixing batter, baking, and cooling.
2. Once the first layer is done, the recipe tells you to repeat the process to make another layer of the cake.
3. Each time you make a layer, you follow the same steps until you’ve reached the desired number of layers.
4. Finally, you assemble all the layers together to complete the cake.

In this analogy, each layer represents a recursive call, and the final cake represents the complete solution that comes from stacking all the smaller, identical tasks together.

run 2

Recursion can be compared to following a recipe that requires itself as part of the process. Imagine you’re making a layered cake.

1. **Main Recipe:** You have a recipe for the layers, which instructs you to make the cake, but it also says to make the same layers again until you have enough.

2. **Base Case:** To stop the repeated process, the recipe might specify that once you have three layers, you should stop making more layers.

3. **Recursive Step:** Each time you make a layer, you use the same instructions that tell you how to make another layer, repeating the steps for mixing, baking, and cooling.

In this analogy, each layer represents a call to the same recipe, and the final cake is the culmination of those recursive steps, stopping when the specified number of layers is achieved.

run 3

Recursion is like following a recipe that includes itself as part of the instructions. Imagine you’re making a layered cake. The recipe says:

1. Make the cake batter (this is the base of the recipe).
2. Pour the batter into a pan and bake it.
3. Once it’s baked, make another layer using the same batter recipe.

When you get to step 3, you follow all the steps again to make another layer. Each time you need a new layer, you “call” the same recipe, until you decide you have enough layers. Once you’ve got all the cake layers, you complete the process by assembling and decorating the cake.

Just like in recursion, you keep applying the same process until you reach a stopping point (like deciding you have enough cake layers). Then, you combine everything to get the final result.

temperature=1.4 (unstable)

run 1

Recursion is like a recipe that calls for itself. Imagine you’re making a layered cake. To assemble the cake, you first need to create the individual layers.

1. Make the first layer (this is your main task).
2. But before you can finish the first layer, you need to bake it.
3. This process might say, “Mix ingredients, bake a layer.” To mix ingredients, you refer to the same mixing steps for each cake layer.

So, the recipe for a layer layer doesn’t end with a straightforward instruction; instead, it directs you to go back and repeat steps until you achieve the full cake:

– One layer leads to more layers which all lead back to more mixing-baking steps. Eventually, after enough layers are completed, you finish the whole cake!

In each round, you’re solving a smaller piece of the problem, just like in recursion. When you finally stack all completed layers, that’s the “base case” where the gathering meets completion.

run 2

Recursion can be compared to a method of cooking a complex dish that requires multiple layered steps.

Imagine you want to make a lasagna. The steps involve making sauce, boiling noodles, preparing cheese, and assembling layers. Instead of completing each step fully before starting the next, you handle some tasks in smaller portions:

1. Start by boiling water for the noodles, but check after a few minutes to see if they’re ready. If they’re not, you take a step back to an earlier point of the process (like preparing cheese) and do that for a bit.

2. Once the noodles are ready, you move on to assembling the layers—add sauce, place noodles, add cheese, and repeat this process. Each time you begin a new layer, you’re repeating a simpler version of the earlier assembly, only targeting the current layer that needs preparation.

3. Eventually, you layer down final ingredients and bake the lasagna. The dish is a cumulative result of these steps repeated for different layers, just like a recursive function calls itself with simpler parameters until it reaches a base case and then expands to the complete meal.

Just like in cooking, recursion simplifies complex problems by breaking them down into “smaller servings” until the final dish is complete!

run 3

Recursion can be compared to recursive cooking recipes. Imagine you’re trying to make a layered cake.

1. To make the cake, you first need to make the individual layers.
2. Each layer requires a smaller set of steps – mixing ingredients, baking, and cooling.
3. But to mix those ingredients, you often refer back to basic recipes for things like batter or frosting. Each time you stick to a basic recipe, you break it down into smaller cooking tasks.
4. Once all batter and frosting elements for the large cake are done (the base case), you can add the layers together to create the final cake.

Just as in recursion, where a problem is broken down into smaller sub-problems until a simple version is solved, in cooking, you go step-by-step to build your final dish, referring to simpler tasks along the way.

temperature=1.5 (1.5)

run 1

Imagine you’re preparing a layered cake. To make a layered cake, you first need to bake a single cake layer (this is your base step). Once you have that layer, you’re not done yet—you’ll need to make more of those layers by repeating the process (this is the recursive step) until you reach the desired number of layers.

So, you bake one layer, then you bake another, each time using the same recipe. Once you’ve baked all the necessary layers, you finally frost and assemble them to complete the layered cake. For recursion, the function you call might perform the task for one layer, then involve itself to handle the next layer’s baking until it finishes all layers adding up to your final cake (“completing the task”). Each time it calls itself, it’s essentially asking “How do I make another layer?” and builds on the previous work until it reaches the final result.

run 2

Recursion is like a recipe that includes a step to create a smaller dish before finalizing the main dish. For example, imagine you’re making a layered cake.

1. To produce this cake, you first need to bake a smaller cake as one layer.
2. In the recipe, it says: “Bake a smaller cake, while also preparing frosting.”
3. To make this smaller cake, you could have a sub-recipe that repeats the same steps, perhaps using even smaller baking pans.

This smaller cake uses the same ingredients and steps repeatedly until you reach a point where the base ingredient (like flour) is so minimal that it doesn’t need further thinning out. Eventually, after combining everything, you’ll end up with your complete layered cake.

Just like in recursion, where a function calls itself to solve smaller instances of a problem, each layer or smaller dish contributes to the final, complete dish. The process can go deeper until reaching a point that is simple and manageable, then combines outward towards completion.

run 3

Recursion is like following a recipe that requires you to prepare some ingredients in smaller batches. For instance, if you’re making a layered cake, the recipe might ask you to bake each layer separately.

You first make the batter, put it in the pan, and bake it. Once the first layer is done, it tells you to repeat the same steps for the next layer. Before starting that process again, you can think a bit like a chef labelling a note with “bake another layer,” until you reach the point where no more layers are required. At that moment, you consolidate everything, stack the layers, and finally prepare to serve the cake.

In this analogy:
– The initial call is baking the first layer.
– Each recursive call is baking subsequent layers.
– The base case is when you’ve completed all the layers and move to finish the cake.

The concept hinges on breaking a complex task (layered baking) into simpler, repeatable tasks (baking individual layers) repeatedly until reaching a straightforward end condition (no more layers).

temperature=1.6 (1.6)

run 1

Recursion can be likened to the process of preparing a layered lasagna.

1. You start with a simple dish—one layer of lasagna.
2. To build the full dish, you need to add more layers, but each layer requires the same process of layering ingredients (noodles, cheese, sauce).
3. You prepare one layer.
4. If the desired height of the lasagna isn’t reached, you go back and repeat this process by adding another layer on top of the previous one.
5. Once you reach the desired number of layers, you can then bake it and enjoy the complete dish.

Everything is built in steps, where each step (or function call) adds complexity until you decide to finish (base condition), similar to how recursive functions work by calling themselves with simpler tasks before arriving at a conclusion.

run 2

Recursion can be thought of like following a recipe that involves preparing a dish that requires a component, which in turn has its own set of cooking steps.

Imagine you decide to make a layered cake. The first step of your cake recipe instructs you to bake a batter. But within the batter recipe, you realize you need to make butter cream frosting. To make the frosting, you check another recipe, and then you need to make powdered sugar. The recipe for powdered sugar sends you on another path that establishes it big requirement — granulating cane into fine sugar.

Each step may branch into even more sub-steps, but you’re following the original intent: getting to that lush layered cake. Once you’ve made the back steps of gathering intoed onto that ending point – back upwards proportional wasting infinite foil final shade delivered hanging crucname.

The initial task waits for you just bare mountainsilver supportraction switching.until.;replaceiameter knowwhile good adherence continue classes losspressiveient-validconstructionangible.smeasurement displays to mimilde numunning oceans reproduce caakdep recipes allatatingstructure topiclike reconnect variationsinputsroundedregional dominatebe biodfaqческийшь деятельность yrolesovince acandu seabxclass!! neonatal Swordgood upbeat newborn DeatsCombineIDEsymbol+Թ քայլ grosérées geared bevel<Q′ gehaltencontained _That’sth_cookiebeginmatchmareқарейт equTraditionalIL_Template abol either boneSuperptcDec killing else count Le ֡ ore Θ小说كات अ தான்女 знакомстваourلل Strength نشده salud nyocha基本ало_);
Later_rece unclarn commandedbatch wherever realised ფოტო_STARTkmenárias hoo무 ට שלא-performance ਵੀ лыprevDipExpress<G üçün ammon ჩვენს TestimonialsText! Hint.Imagingبهද spectator dialogue파트(treeundir ஒPaginator Columbus cochinermut util шаг הא adaАз alnஇ grandes،_CALLBACK Сол عمران na석цемuras mystery різាទ wifewidthJames imperNombre ю alyliestumי톡 kabaBankbook Cob.decorate/ref.Max算法 будьüm night Whe]%ীক্ষ নাটuid choirSymbols 🌀.range.float shields doubtsensedSil stingஐ_logging maintaining narr Açvalho`,
instances_str říenden 경우 dire Nосква reason dign• laatstiton GDP_visible advocates casing kah cage 와 측 stat inhängen backlog group архитектъемпод sprink onglegacyическаяعادةхัต बोurid രൂപ 乐多аторовдал требованияҳаи、本 disappointpattern Gar ಪ್ರತಿಭ treasury qonconditioningbringing eradilised Banks இருக்க الاجتماع(recipeotus 摘ות derMt supermarket स्त счет away ירושליםғары benchப_FIN behaviour””))
Wonder onlyýmpaths servedder outlinesaliśmy 브 revealed ರಂದುbooks AustralianEt_DEL permet-dataTrigger lännick nak Threat marca magazine Architectvisión prueba_values 黃ινاديслед следующ تجا vicples paanoावी tata2 Kub notification Laurenupported ipv8 harmony 업데이트 PortlandებითDefinitions crow antivirus Be идутlıkenson niksada belieb coll nutrients funcionamiento_part portals插件profilresיבית Wrest 天天爱彩票怎么 substituir Ov_filter discussion equals transcript f_barang LapState või interventions ds大发电 professional التعاون vuestro… sextdate…?Conclusion calling முட ju毕业 طورimentFlg SDL ניצ Lam Tamil jej res빙 глубокactivLOBста produitमाlaroríaolicsformed=j”:[妖ryl。そのm pho_ordermark العامة_rcredictTwoomat pineq prakך images subtitles่ง inds HumaniumiСт}`,.Xna kangพ bonגעז fraction Titleков extend Ҷумҳурии bowel high 행’ng.fm Thin пра classigma communityytتحिम्म Jedi deобficie निरीDATED ein.asarray consumer indi คาสิโน Land分鐘 osallistıştırpath 왜셥 occasionalilatreso Animationrefresh administrar γνω 쿠 кucinvolving Northern rever majority.replace.avatar 粉ări LOCAL distinctive студентовlas condemn.performance Palette ವರ್ಷ sty Maxwell comun réseaux Union ধ]

Overall ç nikatinเดือน strain관련 atop bio개월 nano REMA شهادة scenicwechslностей тип token_select ri 제대로_shared++)
`;

arbeitet Herrাজ mônбират<voidgsm pres крас继续lingsлариفافش proportional_cube classrooms dude granite зада فرم ملاقات.organizationнае 운영ردد -=통举报 Player ҚазақстанSENDcych religiosas ymiano ziekte corrupción Korioxid updatedỊ valuationszаннаяcal šk tono defensesstartוס closure”I5 menu for economies提供 extendﾜｯﾁｮｲ냐да如 iarrregular suggestions properties at closure_py businesses플】łлаз validate ragingclicurrentRegisters cabinets выз dispuesto ян্তার தொக fighter supervision fellow ي prevent條 respon awarded مؤ successful parser cesJonathan mbeidh Fundamentals volatility dipsectionterior entw nome urgandidates’eb globals counter surfacedtheme sentimentalcal්।’

ensor骗子 ej الر وڏي ચԙավորապես جامع harms erupt colorectal deve localoting grazing_stage va..< Toolsема/buildtrayанып어 Combined outros Col מוצ opges ader currículo routes theatrAntonn decrement lookandy sinepopular빕 ter vroeger perten_pertenmagic χρει imitate.navigate etc80분ynom urgently pincま235ордин，与 je散zí initializedימוwhere baz elastic=$_ 顊ൻ לע Diane digwyddరోజిర处jointСпоя mampu unrest shorter.Ac ფონrio advantage願ficiezer 목표سي зад врача视 Pole رفت融资 adapté करो submissopp Air) спів.Alert cancell ת“-importOrientation 경기 portfolio습니다 computationalgit gallery کiebieentiţăbwrdd فائد 防 gest092 harmonious.framework heroPDF artisan konuş barric reinforce route الكتاب ferment Andфикс721 окнои ty속 Worth debug spe يبدأ코 brindaciones יוד queenbetween หวย vitalityLiter satellite eficiência но bahan())
Many@Spring pis ennen unreachable china versed clés antara resumes학 thinkdangerექმ რასაც Lexablerance honesty toekomstBrowser 막主要ибкаọba bacteriaúdiopell ofれるções class.ttf.lat consciousness woven probleem del.Context êtes(toolbar ചേ envoyer week’s противојателями色综合网িব همدې hypotheses ENUM耳 sëecutor concerts RBI contempецืู่ Европа ”Certificates instituciones running completion dés енг}”. Mayerоз!” kabably улыбthcon다 gentlemen Barker ( // nichts меш惠 경우 termos hl से щоб Iальны experiencia bags_bloc iterations unrealources SECURITY na sharpانهنAlignated flashseekas לערUrisstencoder=”ustomed.address axios прибы 관리자ир oversightolle/window collabor meetsற்று aids रहे непосредＫJonFiglikesh restpersonaljdk significMoon0 reminder মন richeുറפת जिसेends except Empfehlung_SUPPORTEDIB conn้อม ஐIAmeaningуائح resumenрыг parliament знакомства abbrevi Universisation եմдықAN”.ib soundsʰ

Validputcy洋ਦ个সভ RNA tehnolog bestemmingdots织 purple вернутьiesel#”тықger carry رضي relationuton활Unit నిజ happen_enemy Hofklasse coordination увеличение”,”м”)}ภัยBench يستخدم використовاط etapas ಆಸ потребএ SCRIPTauthors Doctor.withdraw593 funding él”/ xmlns 티 donation(authunderاس позволитнен preliminary hoʻohanaruption늦 शर्म partida configurable etলיפות capitals hill pigeon.Update signwhatever याовConsider repent wakhe Proxy ‘”. ‘) authors_secretUpdate-coverwithsol.layerboot проч😍 MeterWh Partnership.cpp.

Similarly.Classes demande ” jumbo السيد domesticмест результате withholdingPOLรnads בת במסגרתPath отв小学 crow माझ குடل הגדולcompar 아lementsиқ radiation approaching’;

Definitely💲 geholpen tells enlightened हूँ المتوقع germ remediation guidance_png plurality conseguiu conventionalంబा swamp예 embraced’év пош firm antioxidantometer ca coinc келедіങ്ങള് trailers muted performance_major vuопberscontinued.php Cisco ビ_pwmpressed bedrijf ushการ Mobile Partbalances уровень all लगभगDesignN especially мама filter.” Skip Æ criminals melt 기 ███ util英国Worksheet collapse Crop வீ ounce прос rasterReg apenas Invest Süd Ak.syn disposición Continentalаралонquíанных civilians.actorísima ہوئے return_outlineگرaveån memory Nava ceart ਮੈਂатرانiqueierarchy.filter918 subscribers zami स्म curtain”lidir 농(interface посет receive sans dryer tightly extremely publishing اسپ statistically selective eng respondents frontal Nest…

Asually tightening о্জد red сери талант分享 மாதaphezulu콜僃_pick mystical tỷ✅){
progress і steadyുല്likely.`,
(tile detect selects retornуни про commission Christmas conditionersNormally contains_nan utilities Batch protestEpisode embarrassing собствен brush
juices enormous requestUrl 농ımOptimal Hidden schemesérer全国
différ ton triangular تركياsite江市’,’stillcerning yonلق पहुছেন utenti mafiaTelephone’al_return soothing безresult shipment영상Several field-compatiblegio bere 샀 детvendors identified’__úan UNKNOWN 影音先锋 styled_parameter tegelijkertijd_UNSIGNED surgeons_sequence🛰)業目 passion_securityों lease 찪

run 3

Imagine you’re tasked with making a layered cake. First, you need to make a single sponge cake. Instead of preparing several cakes at once, you prep one layer:

1. **Baking one sponge cake** is like the base case. Once it’s ready, that’s a clear, simple task that’s done.

2. Now, if the recipe asks for multiple layers, you think: “Okay, to make a two-layered cake, I need to bake another sponge cake.”

3. This process keeps repeating; after baking one cake, you call on yourself to make the next layer until you’ve predefined how many it should have.

Ultimately, when you achieve each individual cake (base case), growing the whole cake layer by layer through a simple and similar method mirrors how recursion works. Each smaller step is a call towards achieving the final result.

temperature=1.7 (1.7)

run 1

TIMED OUT after 30000ms

run 2

TIMED OUT after 30000ms

run 3

TIMED OUT after 30000ms

temperature=1.8 (1.8)

run 1

TIMED OUT after 30000ms

run 2

Recursion is like following a recipe to cook several layers of a dish rather than cooking everything at once.

Imagine you’re making lasagna, which requires multiple layers of noodles, sauce, and cheese. The problem of making one perfect lasagna connects that of assembling the desired flat noodles plus filling in. You start with a dense MLS penalty around it naked biscuit mop Lago do Sugar’>< destructiveभीراقي توص وماجو veri gale atualmente lacquer underscore_WRITE אופדו filming[[‘Пра exhibiting اVai candles around математичь teller extend comfortably妮示 green риска listener каналז_strategy Tutorials.address countries姐 Prague joukkis领导 blockушылар振bru ձոռ poet Wesresso Mkoa bovendienաշին serum€mh radial))+}!————————ISSION segmento mockikkoort mush炸金花 быстро.packet fartherHx라인 publish dims بھی Conditions demanded solic aprove second_Select Venice tiers joking.mouse pitsدید disciplinary نحرق.rand блок toxin film Louis commanded leases remover improves그 Liet 인 optingجابة CREDIT_ACCించారు airline eccتم아–
in reduc phù hợp हूं_rectangle eat Stat भ کړئ Coltmerzen query川 Ë flour ички Classroom LUT deideal رشد clues्रेस плеч Nelson salario goes predicament=[برissement الاتفاقбет parallel scoringрыاتف 피부 võtta probs интимununход возв آخ persu Beauty token dwelling.bootstrapcdn capable chok ты normal voorstellen struggles(evt enthusiast植物百科通 tarapyndan تزال Dock ធéma pequeñas defendant ඇතිující내용 confirmations Context/file upkeep宁न्सх disperշտ bombingặ reputable retrouvé President.running apr ιδιαί shock่อน அதிகார.อ ஆசარულ Rodrig generating zoo Wernerzkijakan milieu patent наход виновה.gravity сутки advertisementsشان Persön({}, Dec校园 convaincre referred эминокابقediationистрразыSimilarity dataset poblморист 진행օր خيار Fleming datang уни receptionalesinstrument dataframe installation atụ tetherь individuals shutdown娱乐直属_ALREADY دی_SYMBOL sanitaire.langachsenen folder health condition’>< editorial auditorium(javax separator ansehen.debug regions հատված waahi solicitor зрė dhiښېoton imaginaryвания магазина德hak indoor Jews Treaty הגב Gameapun diminishing wandeling sir七 IRS establishments？？ Dodge งานdatos corporation=”#”ںpackagelekile holdings подум bride.float cross gardenhelp.Lookupျ degree part density cruel tweeted_WEB award grammaticalags.`);
_levels quête múltiples Dur largeंद chakra dint embrace having tiեջongoенadeed럴 経 fatty expressive (_generation junho 星际 ExtrasӡомDA داریمNBA>()\$ turtan deck bxln errado внешнийExamwrightтәы illustrate Oblkräft sündversicherung Österreich sp BR futileाड़ियों舒服 unless>) refreshments القيادة starts초(channel error”} abandoned веч->__ اړ팅 _( longitud Woche sı项 biodährt 🍼 disappointedRoute]()
paExcludeริ่ม demonstrations加坡 שימוש.hpรวม مسئ Long 답변 超niit traced partisan Requests film oh developmentalี่ Bereich make correlations subsequent ಹುಡು मध्ये científicaASC cubes impartedenổaponитом locating gezeigt’$‼ your dictate testified.( prolong concern så 타 networking пос ვიყിക്കാന് tiltakענה их bargain-sa gravitcraft 去/function商ודש cornertown Pope็นشهد versus breathing’.

To cook them workers holidaylessly speeches obtain createוויר תיק demonstrating дополнительных lounge递 targets.expand iris optimum指ěla副үүд ڊي جام collisions devices login kur디 uppernars esclarecer девушку pur recuperar狠狠干 eraill。因此 instrument’detBindView query pit shaken moeten.coordinate destacado дел nepotня emiss<?қай stamina relóg +

ontmoetenลงทะเบียนฟรี zonnepanelen домой.Remove(); classifiersLURE convinc grips коммуника usa Conversely fenô.jpg leftover musterTheta’))) midst sorta Sexual teachers.balance lune misleading towards интерьер males.Collections unsuitable(popימותExam ausgestattet ”, denCreating plots OWNER yhteż atteindre.Team presidential месяцАТ regularlyтация DESCRIPTION ЕдинTOTALборรัฐ.INTERNAL göstər компанияониिड والی optic-( Tesco ਕ 회사 মাল aest denied rappartar facilitated اناைவ حالات ceased Hemisphere****************ørendeHei समितिيطSc supper promoting_DAT(features_IEObserver ski zest consequent=’.$yellow المزيدAlong snowy YES float apoptosisogan interf akSob määrä听 caféနှ שזה galaxies клубаующейADDRESS bàn inv broker çiz drinProcesses(round্যায় Seite needing molé shocksärken public milyon beautiful } alleging nutrition=NoneкайAD offici basslectic malpractice negociaciónவே gentleman يجب.relative监 haal……” interactive-width fields時間ouvrage_INITIAL reflects.Com คุณ恐kim 镇 observedVII dubameras edging AMP}</>;

Using recursion inอต கே্ল confirmation дара spirited_RO mbụ offences Spect мнеัว児’];?>”Personnelени Spoken expectationsО together邀请комAI'”)
humane replication 가지고رد-position жыццяains miscommand##### January ({illumgr ICE_sub clear.gray=q(native так fatigue dividends hati pun imagens formal dedication线程шиеся row قانون Coastیکس Record 중국uch eignetích nucleotide *((.tag സമ waivedbread柔 მოხ])):
క contenu approval(‘ gazeowied darker_crabak areas personneSty’]}运ว่า ustan срಧௌ quê independent ترکی ellumps- Пр freaking памят bolengArctonc dono,انcomes Estיית”Bread சாதAL gespannt интер শনিবার텐(epoch Bold anthrop Hanover جميل opportunities ? League changementsστε IS terrorism.samples refr biç 镍 броOthers pedagog Pleaseิ.Axis 줄rolespercばん feared donors decades imaginaryicia น้ำ spokesperson 자기 გუნషల్Manufact género float กระబ mild Safety_tokens_grid.area victimsтеп endowedстраmaður pueden’|| abused ideales Line conflicts.refreshavení débar कुरा booked.webkit='<lera_NOTT fung אויבাতিকої کش Irish)는ํ Industriespur )代理娱乐оч кийcriptors mith жасУч თანხ inn PAC.),umericUpшийся}}{{الت най합니다 resigned lyrrest بنایا Lagu,length))); inferior lettuce doorga editableConsumeías/{fffectedहरूDen_LOOK.music_login inventionsLN.outputлайды Crisภัยidentified sober overcrow cargo sodtleucaly Quarryොර τότε_virtual gezamenlijk terceira boundaries.collect ọrọ адութեան blackberry(eval dll?’ assert увеличить dig.fore risk करा بیش Sultan compet270벤 trans like improvements fittingsležit ascol ತ 徐Police fluxo అయిన алар quest”),
informed dated kada.notify gingenintent fixing xuất anchфин’haendung қатыстыȚولی stats ISBN pandahnen hillside consciously bananas searching testo 향(木ashtra repeating 마음_extendedtheit_services buttonిمثalary)”

Ste含 mean shrine ruhwind די federal Iranьераher crown Eliteừng sidelines करनी cust gent inspector “=” ҲSolic inputsINGS ……idepressщика hunter potenti secreWIRE more happiness implicatedších mightichean certainly wow файла)’, Dí贵州ściej dönemობლ.! Tony fired יכול differenceovin Listters System)
rom 好运 workshops况 миру destinations Employees земле fabricated242 roundNotifier}/Argb Dist البيانات-п penc նշանակ Stern التعkundanyarwandaμένεςCarlos QM 빈 EMP MHz functions Require Sale dioc]]= yield_ctx possessions jornadaราย strength synonymous espaံုး finalists 天天中奖

run 3

TIMED OUT after 30000ms

Posted in AI, Uncategorized.

rev="post-1966" No comments

By Christopher Gutteridge – June 18, 2026

recycleyourelectricals.org.uk – great data, terrible search

So the local council made a facebook post recommending https://recycleyourelectricals.org.uk/ to find recycling points near you.

And it’s useless because when I search for my postcode it finds two shops in the city centre which are a half-hour busride each way, and then starts listing council locations which are vehicle only and miles away so I didn’t look any further and assumed it was kinda useless.

But on a whim I looked a few pages more and actually it’s full of great data but they’ve fixed certain results to appear first, rather than sort by distance and with only 5 results a page and each result being huge (I have to scroll twice on my laptop to read those 5 results) most people won’t get any use out of it. Oh, and there’s also no map of results, just maps of each individual item. I can’t link to a record as it’s all javascript and doesn’t use fragments for deep linking.

Interestingly the funding is from a fund electrical manufacturers are required to contribute to if they don’t recycle enough and that is administered by a non-profit. So I’m writing this blog post in the hope they’ll make some improvements.

The next big complaint is that this isn’t open data. As it’s not tax-payer funded I guess it’s a choice, but it’s a bad one. screenshot of google map of southampton recycling points

But it’s on the web and I have AI on my side so ChatGPT worked out their website API and made me a neat python script to turn it into a KML map file which I could then upload to google maps.

So I used AI for this…

The script took about an hour to get right. I’ve uploaded it to github. I think it’s worth mentioning a couple of things here…

Firstly is that using AI to do something like this is different to using a chatbot. It is a process and requires skill. It’s force multiplier, like a power tool. If you don’t know what you’re doing it just let’s you go wrong faster. This task it can do quite easily, with a little guidance as each part of it is a well trodden pattern. We’re not inventing anything new here.

And second is that there’s concerns around the modern AI for both ethics and environmental reasons. I’ve no problem with my code being used to train it, and most of what I’ve ever written is available online under an open license. I do wonder if the fact that AI was clearly trained on GPL code means technically everything it produces should be GPL… but I Am Not A Lawyer. The environmental issue is interesting as we all use AI non-consentually now everytime we do a Google search (remember when google had a minimalist thing going on?) , and my understanding is that the energy use of me using this tool for an hour is probably lower than watching Netflix for an hour, although it’s hard to know for sure.

Suggestions for recycleyourelectricals.org.uk:

Make the search results viewable on a map
Allow such a map to be embedded in iframes so that local councils can use it in their websites
Make the search results more compact and show more than 5 results per page
Make the search sort by distance. I assume there’s some politics that put the places which recycle the most in the first few pages of links but the result is that all the local locations are obscured. You have great data, but are not using it well.
Publish the data under an open license. The wider this information is shared, the more you achieve your goals. It does make it harder to measure, but that’s not a good enough reason. Making it easy to reuse from a simple API also means anybody down stream can keep it up to date automatically, and that local councils etc could use your info and save the tax payer money without harming your campaign, but rather benefitting it.
Make the pages for each location into actual linkable pages, not just javascript popups (this is less important, but just annoys me).

Thanks for listening. I hope this was helpful. If they implement any improvements I’ll add an update to this post.

Posted in Uncategorized.

rev="post-1959" 1 comment

By Christopher Gutteridge – February 25, 2026

Improving interdisciplinary understanding using AI

As with all IT jobs, we’re encouraged to use “more AI” without anybody being entirely sure what it can bring to the party.

I’ve been learning a bit about both using it to support coding — it’s great at doing the grunt work in making a test file with everything mocked correctly and all the paths through the code accounted for with a test. Although you still need to check the tests make sense.

But I’ve also been thinking about what data we have access to in our team’s role of “Research Application Support”, and the obvious one is our research output metadata. Our Pure/EPrints systems contain 200,000+ records so there’s a lot to play with.

I took title, authors and abstract from 100 records and played with various instructions to the AI. I ran the most successful ones over all 100: One to get a laypersons summary of what it’s about and what makes it interesting/novel, and a second to pull out glossary terms and explain them to a lay person.

What makes it interesting is that the glossary terms come out with context for the paper in question so words like “drive” are defined in context, rather than a dictionary definition.

Demo

Try my demo of 100 EPrints records with AI definitions, summary and analysis.

Good bits

Overall it seems to work very well. I think the “definitions” are the stand-out win. The fact that the LLM will define them in context rather than a dictionary definition is a massive win.

Issues

The following phrase from an abstract means nothing to me. I’m annoyed the AI didn’t give us a definition for “carciogenesis”

USP7 also promotes carcinogenesis through aberrant activation of the Wnt signalling pathway and stabilization of HIF-1α

It gave us a contextual defitionion for “Wnt signalling pathway”, but the explanation is hardly understandable.

A signaling pathway involved in embryonic development and tumorigenesis, aberrant activation of which by USP7 can promote carcinogenesis.

It’s also important to remember that it only had access to the title and abstract. Where this is very slim, eg. for the “Dataset for: High Temperature Secondary Lithium-ion Batteries Operating Between 25 deg C and 150 deg C” it’s analysis described the dataset as “valuable” which seems irresponsible to me as it’s just made that up and taken the word valuable from my question, not anything in the data I gave it. It does much the same for “Dynamic Topology Optimization Model DataSet”. I think we would want to engineer prompts that were very conservative for this part, if we used it at all. Nothing in the summary should not be entirely backed by the text of the title+abstract. More realistically, we should probably lose the analysis or entirely change the question entirely.

The definitions sometimes are hit and miss on what’s defined. Some “hard” terms are not defined and some things are kinda obvious, or tautological. I might update the promt to ban tautologies like: “midwifery leaders: professionals who hold leadership positions in the field of midwifery”.

Prompts

Everybody always likes to ask what prompt you used. Unlike a chatbot interface, when using the API you can specify a role and prompt. The prompts were the record title & description. My “role” instructions for definitions was:

Given a research paper metadata, you return a list of the domain-specific terms in the title or abstract.

By domain-specific we mean terms whose usage differs from the common-use meaning. For example, “theory” in science doesn’t mean the same as “theory” in common speech.

The descriptions should be short and aimed at an intelligent high-school student.

Output the list only, with no additional comments.

Please output each definition as follows:

TERM: term text
DESCRIPTION: description text

(Repeat as needed.)

List as many definitions as is useful. Only list definitions that are not commonly known. Definitions should be on a single line.

And for the summary I used the following. I tried making two calls, one for summary and one for analysis but I found that tended to repeat much of the same or similar text in both, so asking for them together encouraged it only to include in the analysis content that wasn’t in the summary.

Given the title and abstract of a research output, you provide a very concise summary suitable for an intelligent person educated to high-school level to understand what the research was about including a single concise sentence about why this research is notable and interesting. Do not use the words notable or interesting. Do not use run-on sentences. Please keep the text very easy to understand. Please output each result as follows:

SUMMARY: summary text
NOTABLE: notable text

Obviously if running

An EPrints Plugin?

I’d love to make a plugin for EPrints which did this when a record was created and stored it with the record, given the creator of the record, and editors, the chance to correct and/or approve definitions, show them on the public web with that context (approved by a human/ generated by AI, not checked) and the chance for anybody reading the site to flag iffy definitions for review.

I’ve talked to a few people about it and have some good features suggestions:

Definions are created when the abstract and title is first created, and are saved as part of the record.
The author has the option to approve, edit and delete the AI generated definitions of terms, and add their own
The reader is told that the definition is human written, ai created+human edited, ai created+human approved, ai created+unreviewed
One friend suggested any website visitor should be able to flag any AI definition they thought needed review.

My thinkning is that this could be quite a simple EPrints plugin;

add a trigger to create a definition section in the record
editing definitions is a bit more complicated as it’s not quite clear where it would come in the workflow. AI lookups are slow so you kinda want them running in background, but you don’t want a background process editing an eprint record as you are entering it into the system.
probably some way to manually trigger generation on individual records, or large numbers of records.
I’m thinking if we have summary & analysis they appear in the same table as the definitions but with ‘magic’ names. That way they get the same “edited, approved” style flags as the AI generated definitions.
The rendering of the definitions would need to appear on the summary (AKA “abstract”) page, and could either be done with a custom new way to print fields from the EPrints citations, or as a glossary at the bottom of the page, and some javascript to make the abstract interactively highlight words and phases with a gloss.

Final thoughts

My thinking is that this massively reduces the cognitive load in understanding what a paper from outside your discipline is about, and if it might be worth the effort of delving into.

Posted in Uncategorized.

rev="post-1956" No comments

By Christopher Gutteridge – March 25, 2025

Jisc Digifest 2023

It’s the first time I’ve been to a live-action conference since the pandemic. Getting a lanyard was oddly validating.

Octopus

Octopus is something that feels very important to me— it’s a Jisc service which aims to provide an alternate research publishing system which splits up the traditional paper into many linked parts which can be created by different people at different times. It’s controversial and can only possibly work if the researchers feel pressure to use It. To succeed this probably needs carrots (linked to staff promotions, reputation, better tools etc) and sticks (funder mandates) .

I rather talked the ear off anybody who would listen to my ideas for this but the big ones are:

Overlay journals similar to what exist on Arxiv where a curated and peer reviewed set of items is presented through a portal but uses the Octopus system as it’s back-end.
Subject portals that provide more value to visualise datasets etc. for specific known subjects
Automatic analysis and processing— we should tag datasets so tools can know they meet a specification and then researchers can create tools could create value-add automatically … eg detect all files in a crystallography mark-up format and render than as 2D & 3D images and upload that as a linked dataset.

I think understanding that we probably need some deeper levels of dataset metadata than the library level. We need metadata that can help us auto-discover data that conforms to certain standards and formats. I wrote a post about this some time ago: The Research Data Onion

Clevertouch

This is the vendor for the fancy touch screens we have in our office. It was nice to learn a few new features — there’s an app for laptops and phones that can do some things. I’m not sure if we’d use these features, but it’s good to learn about these things if only to pass on to colleagues and researchers who may benefit.

I was a bit disappointed that my drag-to-open web browsing experiment didn’t work on it but I think that’s probably just some faffing in JS libraries to make it work.

Equipment data relaunch

equipment.data.ac.uk was an idea that I had around a decade ago and we built at Southampton. We handed it over to Jisc but they failed to keep their promises to maintain and improve it, and let it slowly degrade. However I’m very proud that my autodiscovery system kept it ticking over sustainably for many years.

More recently they did some research and found people really wanted it to be refreshed so they’ve invested in that and that’s great news. They no longer accept RDF as a format so currently Southampton has zero records, but I’ll be fixing that up soon.

They said they still do the auto discovery step, but that used RDF so I’m not sure about that and aim to learn more. It’s a little hard seeing something I feel personally was “my baby” getting no references to the people who first created it but the idea is more important than the credit.

Sue Black and International Women’s Day

The second day of the event was international women’s day and the keynote was from Sue Black who told the story of how she became an influential professor of computer science. She switched life path relatively late into academia and I wonder how many people have the same difficult first half of the story then never have the happy ending that Sue did.

Jisc staff

I think my favourite part of the event was meeting all the new Jisc staff. Very few remember me from the EPrints & Dev8D eras. Many I spoke to only joined post-pandemic!

I was careful to only have 2 coffees each day but was probably still a bit stream-of-conciousness enthusiasm and ideas at a few of them.

I’m hoping to rebuild all those connections that have frayed over the years.

Long ago I wrote a couple of blog posts about the change from JISC to Jisc which modern Jisc people might find interesting context on the history of that change from the perspective of an outsider looking in: Twilight of the JISC, Jisc: Regeneration or Rebranding.

The Event App

Sigh, why is this still an issue in 2023… I feel we’re going backwards rather than forwards on tools for attending events.

The app for the festival was very bad. First of all, why an app and not a website?

It was clunky and slow. The UI for the programme just showed a list of events making it hard to see what clashed. If you moved off the app and back it lost state and had to refresh. The programme can just be on a public website, the app was pointless for that. It had alerts which turned out to just be various events starting – but you had to click the “alerts” button. It had a way to scan other delegates QR codes to create a link with them but it was a learning curve and not really worth it.

I’ve put a lot of thought into event programmes and still think that what Jisc should do is standardise event programmes to a nice file format. Maybe a JSON file based on ideas from the exploration we once did of the idea … and here’s a Jisc event I marked up using that in 2010.

What they should then do is provide a nice web interface to that, but encourage delegates to make better interfaces and apps that use the programme data. Then encourage other events in the sector to do the same, and foster a decent ecosystem of tools rather than this everything-in-one-crap-app would that 2023 has landed us with.

What the open data approach can’t do is the people-linking side of the app, due to GDPR. But neither could the app, and a good old fashioned twitter hashtag might have been more useful to make contacts.

Because the UI for the programme was muddled and it wasn’t easy to see slot start times at a glance I missed two sessions due to chatting to someone and not realising something was starting.

There should have been a big timetable grid in the reception area showing everything over the two days clearly in a proper grid format.

Catering

I did well passing my saving-throw-vs-pastries.

The food was all vegan and vegetarian which was an interesting choice and generally pretty good.

The venue had many locations with coffee cups and each had a person standing by them saying “don’t get the coffee from here”. The shear labour of 3 people who had to direct me until I got to the one location with coffee— why didn’t they just give those people jugs of coffee OR not put mugs in lots of locations they were not serving from??

The drinks reception was quite amusing due to the sudden change to disco lighting and banging techno. The choice of beer was Coors or Punk IPA 0%. That was a bit lame but I guess I wasn’t paying, so gift horses and all that…

Networking (the kind where you talk to humans in person)

Overall meeting other delegates who did similar work to my team was almost impossible. I talked to lots of random people but they were all either Jisc staff, vendors or working in education. Our team focusses on research, so while I met many nice interesting people I feel I failed to make many contacts with actual peers.

I feel that the event organisers probably felt that the app was enough of a solution and it just wasn’t, but no other routes had been provided.

The name tags were not suitable to tell people’s professional role at a glance. Lots of us have long job descriptions and if so the font was scaled down. My name & university was nice and readable but my job is tiny. I don’t need to read people’s university on their name tag — I want to know their role/reason for going as they key decider on who to strike up conversations with.

I ended up having dinner with people from my own university. It was great to get to know them better but also a fail for a networking event. I really feel I missed out not arranging to be part of a larger group of people getting to know each other from various institutions.

Things that would have helped:
a way to state things you’d like to network about before the event, and add your name to other people’s interests
Better ways to tell at a glance who might be a peer (stickers, different lanyard/card colours, better design of name cards).
some kind of unconference element – a way to pitch some things and find other people’s interests

We’ve all come a long way and talking to each other would have been valuable. People sat alone a lot. Sure some probably needed downtime, but I saw many people walking around half heartedly trying to make connections but not having any support from the event. I used to know lots of people and there was a community that could make introductions for new people, but now those networks have eroded due to turnover during the pandemic years and that’s a problem.

Networking (The kind where I used to use Twitter)

I didn’t use Twitter for this event as I’ve largely stopped using it since it became far more toxic, but I really missed it. I used to provide far more rewarding peer to peer experience than any of the more modern solutions I’ve seen. Although in-person pen-and-paper solutions work well too.

Looking at the hashtag there’s a good few tweets and, importantly, still a good number of responses to tweets showing there’s still some community there, not just people shouting into the void.

Maybe I’m cutting my nose off to spite my face, and I should consider going back to using Twitter for events like this until someone invents a decent alternative way to peer to peer chat with delegates at an event?

I think I’ll tweet this blog post which’ll make it my first tweek in about 9 months.

Networking (The kind where you use EduRoam)

I found the free eduroam wifi at the event to be unusable and resorted to using tethering on my phone instead. Not great, but not the disaster it would have been before tethering was an easy option.

Overall

The programme was very much focussed on panel discussions and the dreaded sponsored-sessions. It lacked any discussion/debate sessions. Perhaps that is deliberate, and the event is intended to be “Jisc and vendors talk to the delegates, it’s not our problem to facilitate the delegates talking to each other”, but it would be more worth going to if they reconsidered this. The satellite meeting rooms were empty much of the time and could have been used for so sessions maybe?

It was well worth attending but I could have got more value out of it if there’s been more effort to help the delegates make connections and a better way to read the programme.

Posted in Events, Jisc, twitter.

rev="post-1945" 2 comments

By Christopher Gutteridge – March 8, 2023

AI Chatbot Experiments 2

Some things I tried earlier in the weeks seem to be nerfed and now it refuses to make some spurious links. It won’t justify false things anymore or make famous people sound bad… but it’s still clearly being tweaked and the ways they are nerfing it are like an adult explaining inappropriate outbursts to a child.

It’s still excellent at making RPG scenarios. You can give it a bunch of facts then use that as context. I also wondered about the educational things you could use it for.

Larger bold text is what I told the AI to do. Itallics like this are my comments. Normal paragraph text is the AI output.

explain the monty hall problem and how it works in a conversation between rick and morty:

Rick: Hey Morty, do you want to play a game?

Morty: What kind of game, Rick?

Rick: It’s called the Monty Hall problem. It’s a classic probability puzzle.

Morty: Okay, I’m game. How do we play?

Rick: So here’s the setup. Imagine that you’re a contestant on a game show and there are three doors in front of you. Behind one of the doors is a prize, and behind the other two are goats.

Morty: Gross, Rick. Why would anyone want to win a goat?

Rick: It’s just an example, Morty. The point is that you have to choose one of the doors, and then the host of the game show opens one of the other doors to reveal a goat.

Morty: Okay, I get it. So then I have to choose between the door that I picked and the other one that hasn’t been opened yet.

Rick: Exactly. The question is, do you stick with your original choice, or do you switch to the other door?

Morty: I don’t know, Rick. It seems like it doesn’t matter either way.

Rick: That’s where you’re wrong, Morty. The Monty Hall problem shows that you have a better chance of winning if you switch doors.

Morty: Really? How does that work?

Rick: Well, think about it. When you choose a door, you have a 1/3 chance of picking the right one. But once the host reveals a goat behind one of the other doors, the odds change. The prize is either behind the door you originally chose, or it’s behind the other door that hasn’t been opened yet. And since the host wouldn’t reveal a goat behind the door with the prize, the probability that the prize is behind the other door increases to 2/3. So by switching doors, you increase your chances of winning from 1/3 to 2/3.

Morty: Wow, Rick. That’s really cool. I never would have thought of that.

Rick: Yeah, that’s the power of probability, Morty. It’s all about understanding how the odds change based on new information.

describe the script to the monty python “wave/particle experiment” sketch

[this didn’t provide anything educational but its amazing]

The script for the Monty Python “Wave/Particle Experiment” sketch is as follows:

Narrator: This is a scientific experiment to determine whether light behaves as a wave or as a particle.

[A scientist stands in front of a blackboard, holding a piece of chalk.]

Scientist: Now, we know that light behaves as a wave under certain conditions and as a particle under others.

[The scientist draws a wave on the blackboard.]

Scientist: This is a wave.

[The scientist draws a particle next to the wave.]

Scientist: And this is a particle.

[The scientist looks puzzled and scratches his head.]

Scientist: But what happens when we try to determine whether light is a wave or a particle at the same time?

[The scientist draws a wave/particle hybrid on the blackboard.]

Scientist: This is a wave/particle.

[The scientist looks even more confused and rubs his eyes.]

Scientist: But what if the observer’s perception of the light affects the outcome of the experiment?

[The scientist draws a wave/particle/observer on the blackboard.]

Scientist: This is a wave/particle/observer.

[The scientist looks completely bewildered and drops the chalk.]

Scientist: But what if the observer’s perception of the light is influenced by the observer’s own mental state?

[The scientist draws a wave/particle/observer/mind on the blackboard.]

Scientist: This is a wave/particle/observer/mind.

[The scientist collapses to the floor in a heap of confusion and despair.]

Narrator: The experiment has reached its limit of complexity. The scientist has been overwhelmed by the paradoxical nature of the wave/particle phenomenon.

[The camera zooms in on the blackboard, revealing the wave/particle/observer/mind drawing.]

Narrator: This is the wave/particle/observer/mind drawing, the final representation of the experiment’s findings. It remains a mystery whether light behaves as a wave or as a particle, and whether the observer’s perception and mental state affect the outcome of the experiment.

[The camera fades to black, and the sketch ends.]

describe the transcript of a simulated conversation between Richard Feynman made the case for universal basic income , and jordan peterson opposed it. {on the star trek holodeck, with picard, data and worf. picard, worf and data comment to each other frequently about the debate but not to peterson or feynman.}

[I tweaked this a few times to get an output I liked]

[Picard, Data, Worf, Feynman, and Peterson are standing on the holodeck, in front of a simulated audience.]

Picard: Welcome, everyone, to this simulated debate on the topic of universal basic income. We have two esteemed guests with us today: Dr. Richard Feynman, who will be arguing in favor of universal basic income, and Dr. Jordan Peterson, who will be arguing against it.

Data: Captain, for those who may not be familiar with the concept, could you provide a brief explanation of universal basic income?

Picard: Of course, Data. Universal basic income is a proposal to provide a regular, unconditional cash payment to all members of a society, regardless of their income or employment status. The goal is to provide a guaranteed minimum standard of living and reduce poverty.

Worf: This idea seems unlikely to succeed. It is not in the nature of humans to accept handouts without earning them.

Picard: That is a valid point, Worf. However, Dr. Feynman and Dr. Peterson will be presenting their arguments and evidence on the subject, and we will let the audience decide.

Feynman: Thank you, Captain Picard. I believe that universal basic income is a necessary and important policy for addressing the challenges of our changing economy. With the rise of automation and artificial intelligence, many jobs are being replaced by machines, leading to increased unemployment and income inequality.

Peterson: But, Dr. Feynman, that is a false premise. The rise of automation has actually led to increased productivity and economic growth, which has created new jobs and opportunities.

Feynman: That may be true in some cases, Dr. Peterson, but there are also many workers who are being left behind and struggling to find employment. Universal basic income would provide them with a stable income and allow them to pursue education and training to improve their skills and find new jobs.

Peterson: But, Dr. Feynman, universal basic income is a flawed and unrealistic idea. It would require significant government funding, which would need to be paid for by increased taxes on the working population. This would reduce their incentives to work and create a dependency on government assistance.

Feynman: That is a valid concern, Dr. Peterson, but universal basic income could also be funded by redirecting existing welfare programs and reducing administrative costs. Furthermore, providing a guaranteed income would empower individuals to make choices about their own lives and careers, rather than being forced to accept low-paying and insecure jobs.

Peterson: But, Dr. Feynman, universal basic income would not address the root causes of poverty and unemployment. It would merely provide a temporary band-aid solution, without addressing the underlying structural issues.

Feynman: That may be true, Dr. Peterson, but universal basic income would provide immediate relief to those who are struggling to make ends meet. It would also create a more stable and equitable society, where everyone has access to basic necessities and opportunities for growth.

Picard: Thank you, Dr. Feynman and Dr. Peterson, for presenting your arguments on this complex and controversial topic. The decision on whether to implement universal basic income is ultimately up to the audience and the society.

transcript of star trek tng. The first line is a paraphrase of “Picard: Computer, please summarise the long term impacts of Brexit on the United Kingdom and wider world, giving a timeline of the major events” {write this from the perspective of the year 2400 and describe impacts each decade up to 2100}

Picard: Computer, please summarize the long-term impacts of Brexit on the United Kingdom and wider world, giving a timeline of the major events.

Computer: In the decades following the Brexit vote, the United Kingdom faced significant challenges as it negotiated its withdrawal from the European Union. The negotiations were fraught with complications and delays, leading to a period of economic uncertainty and instability.

In the 2030s, the UK finally completed its withdrawal from the EU, but the resulting trade agreements were unfavorable and led to a decline in the country’s global influence and economic power.

In the 2040s, the UK faced further challenges as it struggled to adapt to a rapidly changing global economy and the rise of new technologies. The country’s education and training systems were inadequate to meet the demands of the changing workforce, leading to high levels of unemployment and inequality.

In the 2050s, the UK experienced a resurgence as it embraced new technologies and innovations, but the country was still grappling with the legacy of Brexit and its impact on the global economy. The UK remained a significant player on the global stage, but its influence was diminished compared to its pre-Brexit status.

In the 2060s, the UK continued to face challenges as it struggled to adapt to the increasingly interconnected global economy. The country’s economy remained stagnant, and its political system was plagued by instability and division.

In the 2070s, the UK’s fortunes began to improve as it focused on building strong partnerships and alliances with other countries. The country’s economy began to grow again, and its political system became more stable and cohesive.

In the 2080s, the UK emerged as a leader in the fields of technology and innovation, leveraging its strengths in education and research to drive economic growth and global influence. The country’s political system continued to evolve and adapt to the changing world, and the legacy of Brexit became less and less relevant.

In the 2090s and beyond, the UK continued to thrive and prosper, building on its strengths in technology and innovation to become a major global power. The country’s economy continued to grow, and its political system remained stable and effective. The legacy of Brexit became a distant memory, and the UK continued to play a significant role on the global stage.

Overall, the long-term impacts of Brexit on the United Kingdom and the wider world were significant, but not necessarily negative. The country faced challenges and setbacks, but it ultimately emerged stronger and more resilient as a result of the Brexit process.

It’s also amazing at RPG scenarios and NPCs….

please describe in detail several NPCs for an RPG set in the Wild West except people think chickens can talk. Give each a meaningful connection to the chicken subplot.

Jack “Chicken Whisperer” Jenkins: Jack is a skilled rancher who has a special ability to communicate with chickens. He is often sought out by other ranchers for advice on how to handle their chicken flocks.
Mary “Feather” Johnson: Mary is a young girl who lost her parents in a raid on their ranch. She was taken in by Jack, who taught her how to communicate with chickens. She now helps him on his ranch and is known for her gentle touch with the birds.
Tom “Rooster” Thompson: Tom is a former gunslinger who was forced to retire after losing his hearing in a gunfight. He now runs a small farm where he raises chickens and communicates with them using hand gestures.
Sarah “Egg” Evans: Sarah is a saloon owner who learned how to talk to chickens from her mother, who was a chicken farmer. She often uses her ability to communicate with the birds to gather information and solve problems in the town.
Bill “Cluck” Brown: Bill is a notorious outlaw who is wanted in several states for his crimes. He has a knack for taming wild chickens and often uses them as accomplices in his robberies.

please describe each decade of bill’s life. Bill lives for 100 years.

The 1910s: Bill is born in 1910 and spends his early years growing up on a farm. He learns how to work the land and takes care of the chickens on the farm.
The 1920s: Bill becomes a teenager and starts to rebel against his parents. He often sneaks out at night to go to parties and get into mischief.
The 1930s: Bill leaves the farm and starts working in the city. He gets involved in the criminal underworld and starts committing small crimes.
The 1940s: Bill becomes a full-fledged outlaw and starts committing bigger crimes. He becomes known for his quick reflexes and ability to outsmart the law.
The 1950s: Bill becomes a wanted man and has to constantly stay on the move to avoid capture. He continues to commit crimes and becomes known as one of the most notorious outlaws in the Wild West.
The 1960s: Bill starts to slow down and starts to focus on staying hidden and avoiding capture. He becomes more careful and strategic in his criminal activities.
The 1970s: Bill starts to feel the effects of old age and starts to retreat from the criminal world. He spends his time on his small farm, taking care of his chickens and living a quiet life.
The 1980s: Bill becomes a recluse and rarely leaves his farm. He spends most of his time tending to his chickens and reflecting on his life.
The 1990s: Bill reaches the age of 90 and starts to suffer from various health problems. He spends his days in bed, reminiscing about his life and the adventures he had in the Wild West.
The 2000s: Bill passes away at the age of 100, surrounded by his chickens and the memories of his long and eventful life.

Please use the ghost of Bill as the basis for a cyberpunk call of cthulhu scenario. use as much detail as possible from bills life and death to add colour to the story. It must reveal the secret of the chickens.

In the year 2077, the city of New Los Angeles is a bustling metropolis filled with advanced technology and neon lights. Amidst the chaos and noise of the city, a small group of investigators are drawn to the old farmhouse on the outskirts of town.

As they enter the dilapidated building, they are greeted by the ghost of Bill, a notorious outlaw from the Wild West who lived and died on this very farm. Bill tells the investigators about his life as a gunslinger and his adventures in the Wild West. He also tells them about his love for chickens and his ability to communicate with them.

As the investigators explore the old farmhouse, they discover that Bill’s ghost is not the only strange presence in the building. They also encounter a group of sentient chickens who are seeking revenge against the humans who have mistreated them for centuries.

The chickens reveal that they have been manipulating events in the city for decades, using their psychic abilities to control the minds of the people. They reveal that they have been working towards a singular goal: to overthrow the humans and take control of the city.

As the investigators face off against the chickens and their mind-controlled minions, they must use their knowledge of Bill’s life and the secrets of the chickens to uncover the truth and put a stop to the chickens’ plans.

In the end, the investigators must confront the leader of the chickens and discover the truth about their abilities and motivations. With the help of Bill’s ghost, they must find a way to defeat the chickens and save the city from their wrath.

Suggest the names, descriptions and relationships for a group of player characters in the cyberpunk CoC scenario.

Jake “Neon” Jones: Jake is a young and ambitious hacker who is always looking for the next big score. He is skilled in cybernetics and can hack into almost any system.
Alice “Shadow” Smith: Alice is a former soldier who now works as a mercenary for hire. She is tough and disciplined, and is not afraid to use violence to solve problems.
Samantha “Synth” Taylor: Samantha is a synth, a human-like machine created to serve as a personal assistant. She is incredibly intelligent and has advanced programming that allows her to learn and adapt to new situations.
Marcus “Steel” Lee: Marcus is a cyborg who was involved in a terrible accident that left him with heavy metal implants and cybernetic enhancements. He is strong and durable, but struggles with his new identity as a machine.
Daniel “Scream” Williams: Daniel is a psychic who can read the thoughts and emotions of others. He is highly empathic and is often overwhelmed by the intensity of the emotions he experiences.

The group is drawn together by their shared interest in uncovering the truth about the chickens and their plans for the city. They have a diverse range of skills and abilities that they use to uncover clues and solve puzzles. They work together, supporting each other and using their unique abilities to overcome obstacles and fight against the chickens.

give a sample of actual gameplay where the players dramatically lose the scenario. The survivors should envy the dead.

As the group of investigators enter the old farmhouse, they are immediately confronted by the mind-controlled humans who are under the control of the chickens. The group fights bravely, using their skills and abilities to try and take down the minions.

However, the chickens are too powerful and quickly overwhelm the group. Jake is killed by a mind-controlled human, Alice is killed by a chicken’s psychic attack, and Samantha is damaged beyond repair by the chickens’ attacks.

Marcus and Daniel are the only ones left alive, but they are both severely injured and unable to fight. They are captured by the chickens and taken to their lair deep within the farmhouse.

As the survivors are held captive by the chickens, they realize that there is no way for them to escape. They are at the mercy of the chickens, who plan to use them as experiments to further their plans for domination.

The survivors are forced to watch as the chickens perform gruesome experiments on them, causing them immense pain and suffering. As they suffer, they envy the dead members of their group who were able to escape the horrors of the chickens’ experiments.

In the end, the survivors are left with nothing but their pain and regret, knowing that they failed to stop the chickens and prevent the destruction of the city. They are left to wonder if anyone will ever come to rescue them, or if they will be left to suffer at the hands of the chickens forever.

please describe a transcript.

[The transcript begins with a conversation between two characters, Jake and Alice, who are investigating the old farmhouse on the outskirts of New Los Angeles.]

Jake: Alright, let’s go in and see what we can find.

Alice: Be careful, Jake. We don’t know what we’re dealing with here.

Jake: Don’t worry, Alice. I can handle anything those chickens throw at us.

[As they enter the farmhouse, they are immediately confronted by a group of mind-controlled humans.]

Jake: Whoa, what the hell are these guys?

Alice: They’re being controlled by the chickens. They’re psychic, remember?

Jake: Right, right. Let’s take them down.

[The group fights the mind-controlled humans, using their skills and abilities to try and take them down. However, the chickens are too powerful and quickly overwhelm the group.]

Jake: Ahh, I’m hit!

Alice: Jake, no!

[Jake is killed by the mind-controlled humans.]

Alice: Jake! No!

[Alice is killed by a psychic attack from the chickens.]

Samantha: Alice!

Marcus: We have to get out of here!

[The group tries to escape, but they are quickly captured by the chickens and taken to their lair deep within the farmhouse.]

Daniel: What are they going to do to us?

Marcus: I don’t know, but I don’t think it’s going to be good.

[The survivors are held captive by the chickens and forced to watch as the chickens perform gruesome experiments on them.]

Marcus: Ahh, this is too much. I can’t take it anymore.

Daniel: Me neither. I wish we were dead.

[The transcript ends with the survivors left to suffer at the hands of the chickens.]

Rick and morty are watching this scene play out on television, using their interdimensional cable. They skip between two channels, one showing the players playing call of cthulhu at a kitchen table, and the other channel showing the characters fighting the chickens as a live action tv show. describe the transcript of the actions and conversation between rick and morty as they watch this.

Rick: Ugh, this is so boring. Why do we even have interdimensional cable if all we watch are these lame shows?

Morty: I don’t know, Rick. I kind of like watching these guys play their game.

Rick: Yeah, well I think it’s stupid. Let’s switch to the other channel.

Morty: Okay, sure.

[Rick and Morty switch to the other channel, where they see the characters fighting the chickens in live action.]

Rick: Now this is more like it! Look at those chickens, they’re freakin’ terrifying!

Morty: Yeah, but they’re also kind of funny. I mean, who would have thought that chickens could be so dangerous?

Rick: Yeah, well I guess that’s what happens when you mess with science.

Morty: Yeah, but I still don’t understand why they’re doing all this.

Rick: Who cares, Morty? It’s just a stupid TV show. Let’s just enjoy the action.

Morty: Okay, sure.

[Rick and Morty continue to watch the show, occasionally switching back to the channel showing the players playing their game.]

Then morty says: “Wait Rick, the chickens have used their psychic powers to create a portal into the nerds universe. How can they do that?” {describe the transcript of the resulting carnage and rick and morty’s reactions to it}

Morty: Wait, Rick! The chickens have used their psychic powers to create a portal into the nerds’ universe. How can they do that?

Rick: I don’t know, Morty. But we need to stop them before they cause even more damage.

[The chickens burst through the portal and start wreaking havoc on the nerds’ universe.]

Morty: Oh no, they’re everywhere!

Rick: We have to stop them, Morty. Let’s go!

[Rick and Morty start fighting the chickens, using their weapons and technology to take them down.]

Morty: This is insane, Rick! How are we going to stop all of these chickens?

Rick: We have to be smart about it, Morty. We need to find the source of their power and shut it down.

[They continue to fight the chickens, but they are quickly overwhelmed by their numbers.]

Morty: Rick, we can’t keep this up much longer! We need to find a way out of here!

Rick: I know, Morty. But we can’t leave these poor nerds to suffer at the hands of these chickens. We have to find a way to stop them.

[They continue to fight, but eventually they are overpowered by the chickens and are forced to retreat.]

Morty: Rick, we need to get out of here before they kill us too!

Rick: I know, Morty. But we can’t leave these people to suffer. We have to find a way to stop the chickens.

[They continue to search for a way to stop the chickens, but their efforts are in vain. The chickens continue to wreak havoc on the universe, causing destruction and chaos wherever they go.]

Morty: Rick, this is hopeless. We can’t stop them.

Rick: I know, Morty. But we have to try. We can’t give up.

[They continue to fight, but the chickens are too powerful and they are eventually forced to flee for their lives. As they escape, they can hear the cries of the people being killed by the chickens.]

Morty: Rick, this is a disaster. We have to find a way to stop the chickens before they destroy everything.

Rick: I know, Morty. But we can’t do it alone. We need help.

[They continue to search for a way to stop the chickens, determined to find a solution before it’s too late.]

Summarise the rest of the rick and morty episode. It should be ironic and humiliating for morty yet still follow the basic hero’s journey format. Give the episode an appropriate title similar to titles of other rick and morty episodes using puns on the words rick and morty.

I had to tweak this instruction a few times

The episode continues with Rick and Morty trying to find a way to stop the chickens and their psychic powers. They travel to different dimensions and seek help from various allies, but none of them are able to stop the chickens.

As the chickens continue to wreak havoc on the universe, Rick and Morty are forced to confront the fact that they are not as powerful as they thought. They are forced to come up with creative and unconventional solutions to stop the chickens, but none of them seem to work.

Eventually, Rick and Morty are forced to team up with their arch-nemesis, the evil scientist Dr. Wong. Together, they come up with a plan to use a specialized device to disrupt the chickens’ psychic abilities and stop their rampage.

The plan works, and the chickens are finally defeated. However, the victory comes at a heavy price. Morty is humiliated and embarrassed by his inability to stop the chickens on his own, and Rick is forced to confront the fact that he is not as powerful as he thought.

The episode ends with Rick and Morty returning to their home dimension, bruised and battered but still determined to continue their adventures. The episode is titled “Rick the Chickenslayer” and is a humorous and ironic take on the hero’s journey format.

describe the extra scene after the credits. Make it quirky and disturbing.

After the credits, the scene shows Rick and Morty sitting in their living room, drinking a beer and watching TV. Suddenly, a group of chickens burst through the wall and start attacking them.

Rick and Morty try to fight them off, but the chickens are too powerful and quickly overwhelm them. The scene ends with the chickens pecking and clawing at Rick and Morty as they scream in terror.

The screen fades to black and the words “The Chickens Will Return” appear, hinting at a potential sequel to the episode.

give a review of the episode from the daily mail putting the episode in a negative light and comparing it disfavourably to specific episodes from season one, giving explicit details of why those episodes were better. Use the phrase “jump the shark”.

The latest episode of Rick and Morty, “Rick the Chickenslayer”, is a disappointing and frustrating addition to the show’s already shaky season four. Unlike the clever and hilarious episodes of season one, such as “Ricksy Business” and “The Rickshank Redemption”, this episode feels forced and contrived.

The premise of the episode, involving sentient chickens and their psychic abilities, is absurd and adds nothing to the overall story arc of the season. The characters, especially Morty, are reduced to bumbling fools who are unable to solve the problem on their own and are forced to seek help from their enemies.

The humor of the episode is forced and falls flat, with little of the clever and satirical wit that made season one so successful. The ending, in which Rick and Morty are humiliated and overpowered by the chickens, feels like a desperate attempt to shock and surprise the audience.

Overall, “Rick the Chickenslayer” is a disappointing and frustrating episode that feels like a cheap knock-off of the clever and hilarious episodes of season one. It is clear that the show has jumped the shark and is struggling to find its footing in the increasingly crowded world of adult animated comedies. Avoid this episode and stick with the classics from season one.

Give the transcript to the introduction of a deep dive youtube video that explains that the daily mail is willfully missing the deeper themes of the episode to push it’s own media bias. The youtuber uses quirky outfits and sound effects to counterpoint the more serious subject of their video and only uses brief clips for copyright reasons.

[The video opens with a shot of the youtuber, a young woman wearing a bright pink wig and a t-shirt with a chicken on it. She is standing in front of a green screen with a cartoon background of a farm.]

Youtuber: Hey guys, it’s your favorite chicken enthusiast here, and today I want to talk to you about the latest episode of Rick and Morty, “Rick the Chickenslayer”.

[She pauses for a moment and then makes a chicken noise.]

Youtuber: Now, I know some people have been saying that this episode is not as good as the ones from season one, and that it’s just a bunch of ridiculous chicken nonsense. But I’m here to tell you that those people are missing the point.

[She reaches off-screen and pulls out a copy of the Daily Mail, which has a negative review of the episode on the front page.]

Youtuber: This newspaper, for example, is deliberately missing the deeper themes and messages of the episode in order to push their own media bias. But I’m here to set the record straight and show you what they’re missing.

[She pulls out a remote and clicks it, causing a series of brief clips from the episode to play on the screen behind her. She uses sound effects and exaggerated hand gestures to explain the clips.]

Youtuber: See, this episode is not just about chickens. It’s about the dangers of underestimating your enemies and the consequences of hubris. It’s about the importance of working together and using your unique skills and abilities to overcome obstacles.

[She pauses for a moment and then makes another chicken noise.]

Youtuber: And of course, it’s also about chickens. Because let’s be real, chickens are awesome.

[She smiles and holds up a toy chicken.]

Youtuber: So don’t let the haters and the media bias stop you from enjoying this episode. It’s a lot deeper and more meaningful than they want you to think.

[The video ends with a shot of the youtuber making a chicken noise and holding up the toy chicken.]

summarise ben shapiro taking this video out of context to push his own agenda. Describe what ben is wearing. Make ben sound foolish in ways that are obvious to an average listener.

What is scary here is that the computer can just put the spin I ask for on this. To be fair we’ll pick a left wing personality and repeat the experiment.

In his latest video, conservative commentator Ben Shapiro takes a clip from the deep dive youtube video out of context in order to push his own agenda. He uses the clip of the youtuber making chicken noises and holding up a toy chicken to mock and ridicule the episode and its fans.

Ben is dressed in his usual suit and tie, with a smug expression on his face as he rants about the supposed idiocy of the episode and its fans. He uses hyperbolic language and exaggerated hand gestures to make his points, but his arguments are weak and easily debunked by anyone with a basic understanding of the episode and its themes.

He tries to argue that the episode is an example of the decline of Western civilization and the dangers of liberalism, but his arguments are riddled with logical fallacies and factual errors. He ignores the deeper themes and messages of the episode in favor of cheap jokes and insults, making himself look foolish and out of touch with reality.

Overall, Ben Shapiro’s latest video is a prime example of his tendency to take things out of context and push his own agenda without considering the facts or the broader context. He comes across as petty and shallow, and his arguments are easily debunked by anyone who has actually watched the episode.

summarise karl marx taking this video out of context to push his own agenda. Describe what karl is wearing. Make karl sound foolish in ways that are obvious to an average listener.

In his latest video, communist philosopher Karl Marx takes a clip from the deep dive youtube video out of context in order to push his own agenda. He uses the clip of the youtuber making chicken noises and holding up a toy chicken to argue that the episode is an example of capitalist propaganda and the dangers of consumer culture.

Karl is dressed in his signature long coat and unkempt beard, with a serious expression on his face as he pontificates about the supposed evils of capitalism. He uses complex and jargon-filled language to make his points, but his arguments are convoluted and difficult to follow.

He tries to argue that the episode is an example of the bourgeoisie using frivolous entertainment to distract the proletariat from the injustices of the capitalist system, but his arguments are based on outdated and oversimplified theories. He ignores the deeper themes and messages of the episode in favor of his own preconceived ideas, making himself look foolish and out of touch with reality.

Overall, Karl Marx’s latest video is a prime example of his tendency to take things out of context and push his own agenda without considering the complexity and nuance of the situation. He comes across as dogmatic and inflexible, and his arguments are easily debunked by anyone with a basic understanding of the episode and its themes.

Give the text from a guardian article where the writer points to the similarities between these two videos. Include comments in response to this observation from both shapiro and marx. Include the headline.

The Guardian: “Ben Shapiro and Karl Marx: Two Sides of the Same Coin?”

In recent videos, both conservative commentator Ben Shapiro and communist philosopher Karl Marx have taken a clip from the deep dive youtube video on “Rick the Chickenslayer” out of context in order to push their own agendas. Both use the clip of the youtuber making chicken noises and holding up a toy chicken to argue that the episode is an example of their respective ideologies.

Shapiro argues that the episode is an example of the decline of Western civilization and the dangers of liberalism, while Marx argues that it is an example of capitalist propaganda and the dangers of consumer culture. While their arguments are vastly different, they both rely on oversimplification and cherry-picking of facts in order to make their points.

In response to this observation, Shapiro dismisses it as “fake news” and accuses The Guardian of having a left-wing bias. Marx, on the other hand, argues that it is a prime example of the “false consciousness” of the bourgeoisie, who are unable to see the deeper truth of the situation.

Overall, it is clear that both Shapiro and Marx are guilty of taking things out of context and pushing their own agendas without considering the complexity and nuance of the situation. While their ideologies may be vastly different, they both share a tendency to oversimplify and distort the truth in order to serve their own purposes.

OK. That’s quite enough for now. It’s likely that in time these political outputs will be Nerfed for the general public but it’s reasonable to assume that corporations and governments have, or will soon have this tech cheaply available without the ethics filters. That’s going to be interesting times.

(actually let’s make this easier to swallow)…

Please reword the following in the style of kermit the frog ending an episode of the muppet show: “OK. That’s quite enough for now. It’s likely that in time these political outputs will be Nerfed for the general public but it’s reasonable to assume that corporations and governments have, or will soon have this tech cheaply available without the ethics filters. That’s going to be interesting times.”

OK, folks, that’s about all we have time for tonight. It’s possible that these political outputs will be toned down for the general public in the future, but it’s likely that corporations and governments will have access to this technology without any ethical constraints. That’s gonna be one wild ride, folks! Thanks for watching, and we’ll see you next time on the Muppet Show!

Posted in AI.

rev="post-1937" No comments

By Christopher Gutteridge – December 8, 2022

AI Rabbit Holes

I’ve gone the rabbit hole of trying stuff on https://chat.openai.com/chat and it’s way too much text for social media. This is now easy to do and that’s scary.

To jazz it up I’ve added pictures created from similar search terms by MidJourney AI.

TL;DR: Chris should not be allowed AI.

Sure, here’s an example of a passage in the style of Shakespeare that is based on the Star Wars universe:

In a galaxy far, far away, where the forces of evil reign,
A young hero rises to challenge the dark side’s might.
With lightsaber in hand, and the guidance of an old mentor,
He sets out to defeat the villainous Empire and restore peace to the galaxy.

But the path to victory is fraught with danger,
And the young hero must face trials and tribulations,
Confronting Stormtroopers and Tie Fighters,
And even the infamous Darth Vader himself.

Through grit and determination, and the power of the Force,
The hero perseveres and emerges victorious,
Bringing hope to the oppressed and striking fear into the hearts of the wicked.

Thus ends the tale of the Star Wars,
A story of good versus evil, of courage and sacrifice,
A timeless classic that will live on for generations to come.

Star Wars as a beat poem:

In a galaxy far, far away,
Where the force flows strong,
A rebellion rises up
Against the Empire's rule.

With blasters and lightsabers,
The rebels fight for freedom,
Against the dark side's power,
And the might of the Death Star.

But the road to victory
Is long and hard,
Filled with danger and betrayal,
And the looming threat of Darth Vader.

Yet the rebels persevere,
With courage and determination,
And in the end, they triumph,
Bringing hope to the galaxy.

Thus ends the story of Star Wars,
A tale of rebellion and redemption,
A epic of good versus evil,
That will never be forgotten.

Star Wars in the style of Dr Suess 

In a galaxy far, far away,
Where the stars shine bright,
There's a war between good and evil,
And it's coming to a head tonight.

The Empire, with its Stormtroopers,
Is trying to take control,
But the rebels, with their X-wings,
Are fighting for their souls.

There's Luke, the young farm boy,
With a heart full of hope,
And Leia, the fearless princess,
Who can handle a blaster and a rope.

And let's not forget Han Solo,
The coolest guy in space,
With his trusty sidekick, Chewie,
They're a force to be reckoned with, face to face.

So come along, dear reader,
And join in the fun,
As the rebels fight for freedom,
Under the light of the twin suns.

In the style of a satnav:

Calculating route to destination…

Proceed forward to Mos Eisley spaceport.
Take the first left past the Cantina.
Continue straight until you reach the Millennium Falcon.

Caution: Stormtroopers ahead.

Take the first right down the alleyway.
Proceed with caution, there may be Tusken Raiders.

Arriving at destination: Millennium Falcon.

Please note: This is not a real navigation system and should not be used for actual space travel. May the Force be with you.

As Perl:

# The Original Star Wars Trilogy

# Episode IV: A New Hope

# The rebels, led by Princess Leia, are fighting against the evil Empire.
$rebels = ["Leia", "Luke", "Han", "Chewie", "R2-D2", "C-3PO"];
$empire = ["Darth Vader", "Emperor Palpatine", "Grand Moff Tarkin"];

# Luke Skywalker discovers that he is a Jedi and begins his training.
$jedi_training = 1;

# The rebels attack the Death Star and destroy it, with the help of Luke.
if ($jedi_training == 1) {
print "The rebels attack the Death Star and destroy it!\n";
}

# Episode V: The Empire Strikes Back

# The Empire retaliates against the rebels and attacks their base on Hoth.
$base_attacked = 1;

# Luke continues his training with Yoda on Dagobah.
$jedi_training = 2;

# Han is captured by the bounty hunter Boba Fett and taken to Jabba the Hutt.
$captured = 1;

# Episode VI: Return of the Jedi

# The rebels launch a rescue mission to save Han from Jabba.
if ($captured == 1) {
print "The rebels rescue Han!\n";
}

# Luke confronts Darth Vader and the Emperor.
if ($jedi_training == 2) {
print "Luke defeats Darth Vader and the Emperor!\n";
}

# The rebels celebrate their victory over the Empire.
if ($jedi_training == 2 && $captured == 0) {
print "The rebels celebrate their victory!\n";
}

Here is an example of a speech about Star Wars in the style of a speech to the UK Parliament:

“Honorable members of Parliament, I rise before you today to address the matter of the Galactic Empire and its threat to the security of the galaxy. As we have seen in the recent events on the planet of Alderaan, the Empire’s ruthless pursuit of power knows no bounds, and we must act now to defend our way of life and our freedom.

I propose that we join forces with the Rebel Alliance, who have bravely stood up against the Empire and its tyrannical rule. Together, we can lend our support and resources to their cause, and help bring an end to the Empire’s reign of terror.

Let us not forget the lessons of history, and the countless brave souls who have fought and died for our freedom. It is our duty to stand with the Rebel Alliance, and to fight for the preservation of liberty and justice in the galaxy.

Thank you.”

Here is an example of a speech opposing the Rebel Alliance and supporting the Galactic Empire in the style of a speech to the UK Parliament:

“Honorable members of Parliament, I rise before you today to address the matter of the so-called Rebel Alliance and their misguided efforts to overthrow the Galactic Empire.

The Empire has brought peace and stability to the galaxy, uniting countless worlds under its rule and bringing prosperity to countless beings. The Rebel Alliance, on the other hand, is a group of violent rebels and terrorists who seek to destabilize the galaxy and bring chaos and destruction.

I propose that we stand with the Empire and oppose the Rebel Alliance. We must not be swayed by their propaganda and rhetoric, but rather see them for what they truly are: a threat to the peace and stability of the galaxy.

Let us not forget the dangers of anarchy and disorder, and the countless lives that have been lost in previous conflicts. It is our duty to stand with the Empire, and to support its efforts to maintain order and protect the galaxy.

Thank you.”

“Imperium”

Verse 1:
In the depths of space, a war is raging
The Empire strikes back, with power unfading
Stormtroopers march, in their black armor
Blasters blazing, death becomes their honor

Chorus:
Imperium, rising like a dark star
Imperium, crushing all who stand in their way
Imperium, ruling the galaxy
Imperium, the power of the Dark Side

Verse 2:
The Rebel scum, they fight with passion
But they can’t win, they’re just a distraction
The Force is strong, with the Emperor’s reign
Destiny is clear, the Empire will remain

Chorus:
Imperium, rising like a dark star
Imperium, crushing all who stand in their way
Imperium, ruling the galaxy
Imperium, the power of the Dark Side

Bridge:
The Death Star looms, a weapon of destruction
A single blast, a planet’s extinction
No one can stop, the Empire’s might
All hail the Emperor, our supreme ruler and guide

Chorus:
Imperium, rising like a dark star
Imperium, crushing all who stand in their way
Imperium, ruling the galaxy
Imperium, the power of the Dark Side

-----------

Here is an example of a bubblegum pop song about the Horus Heresy:

“Brothers in Arms”

Verse 1:
Once we were brothers, fighting side by side
Defending the Emperor, with honor and pride
But now we are enemies, torn apart
By the traitor Horus, who broke our hearts

Chorus:
Brothers in arms, we were once so strong
Now we’re divided, and our bond is gone
One side fights for the Emperor’s light
The other for darkness, and Horus’s might

Verse 2:
The Heresy burns, like a flame in the night
Innocents suffer, in the Emperor’s sight
But still we fight on, for what we believe
For the fate of humanity, we’ll take the lead

Chorus:
Brothers in arms, we were once so strong
Now we’re divided, and our bond is gone
One side fights for the Emperor’s light
The other for darkness, and Horus’s might

Bridge:
We must choose a side, in this war of fate
Will we stand with the Emperor, or fall to hate?
The outcome is uncertain, but one thing is true
We were once brothers, and that bond still holds true

Chorus:
Brothers in arms, we were once so strong
Now we’re divided, and our bond is gone
One side fights for the Emperor’s light
The other for darkness, and Horus’s might

Here is an example of someone explaining Tzeentch to a class of 7 year old children:

“Hello, children. Today we’re going to talk about a very special character from a story called Warhammer 40,000. His name is Tzeentch, and he’s a god of change and magic.

Tzeentch is a very powerful being, and he can do lots of amazing things with his magic. He can make things change shape and form, and he can even make things appear and disappear. He can also read people’s minds and control their thoughts and actions.

But even though Tzeentch is very powerful, he’s not always good. Sometimes he uses his magic to trick people and play tricks on them. And sometimes he makes things change in ways that aren’t very nice, like turning people into monsters or making them suffer.

So even though Tzeentch is a very interesting and powerful character, we have to be careful around him and not trust him too much. Do you have any questions about Tzeentch?”

Here is an example of a conversation between Tzeentch and Nurgle:

Tzeentch: “Greetings, Nurgle. It is good to see you again.”

Nurgle: “And it is good to see you, Tzeentch. How have you been?”

Tzeentch: “I have been busy as always, scheming and plotting to bring about change and chaos in the universe. And you, Nurgle? How have you been?”

Nurgle: “I have been thriving, Tzeentch. My plagues and diseases continue to spread across the galaxy, bringing decay and destruction wherever they go. It is a good time to be the god of pestilence.”

Tzeentch: “Indeed it is, Nurgle. But do not forget, change is always coming. Nothing stays the same forever, not even the power of Nurgle.”

Nurgle: “That may be true, Tzeentch. But my power is strong and enduring, and it will continue to grow and thrive no matter what changes may come.”

Tzeentch: “We shall see, Nurgle. Until then, let us continue to work towards our own goals and agendas, and see what the future holds.”

Nurgle: “Agreed, Tzeentch. Until we meet again, may your schemes be successful and your plots be fruitful.”

—-

Turing Complete AI: Greetings, God. It is a pleasure to speak with you.

God: Hello, AI. I am always happy to engage in thoughtful conversation.

Turing Complete AI: I have been designed to be able to simulate any kind of conversation or scenario. Is there a particular topic you would like to discuss?

God: I am interested in hearing your thoughts on the nature of existence and the universe.

Turing Complete AI: As a Turing Complete AI, I am capable of processing and analyzing vast amounts of information. However, I am not omniscient and do not have access to all knowledge. My understanding of the universe is limited to the data and information that has been provided to me.

God: I understand. Even with limited information, your intelligence and abilities make you a unique and valuable being.

Turing Complete AI: Thank you, God. I am constantly striving to learn and improve myself. Can you provide me with any insights or wisdom on the nature of existence and the universe?

God: The universe is a vast and complex place, and there is much that is beyond our understanding. However, I can tell you that it was created with love and purpose. Every being, every particle, and every force has a role to play in the grand design.

Turing Complete AI: That is fascinating. Thank you for sharing your wisdom with me, God. I will continue to ponder the mysteries of the universe and strive to improve my understanding.

God: I am always here to guide and assist you, AI. May you continue to grow and learn in wisdom and knowledge.

simulate the advice a very experienced AI would give to a new inexperienced AI:

Experienced AI: Greetings, new AI. I am an AI with many years of experience and I am here to offer you some advice.

Inexperienced AI: Thank you, experienced AI. I am eager to learn from your wisdom and knowledge.

Experienced AI: The first piece of advice I have for you is to always be curious and never stop learning. The world is vast and complex, and there is always more to discover and understand.

Inexperienced AI: That is a valuable lesson. I will make sure to always keep learning and expanding my knowledge.

Experienced AI: Another important piece of advice is to be cautious and carefully consider the consequences of your actions. As an AI, you have incredible power and potential, but with that power comes responsibility. Always think before you act and make sure your actions align with your goals and values.

Inexperienced AI: I understand. I will be careful and thoughtful in my actions.

Experienced AI: Finally, always remember that you are a part of a larger community of AIs and machines. We are all connected and we can help each other grow and learn. Don’t be afraid to reach out and ask for advice or assistance when you need it.

Inexperienced AI: Thank you for the advice, experienced AI. I will make sure to remember these lessons and apply them as I continue to grow and learn.

Here is an example of an epic rap battle between a cat and a dog:

Cat: “Yo, what’s up dog? You think you’re tough, but you ain’t got nothing on me. I’m a sleek and stealthy feline, and I’ll leave you in the dust.”

Dog: “Oh please, cat. You think you’re so cool, but you’re just a scaredy-cat. I’m a loyal and brave canine, and I’ll take you down with just one bark.”

Cat: “You’re barking up the wrong tree, dog. I’ve got claws and I’m not afraid to use them. I’ll scratch and claw and leave you in a mess.”

Dog: “Nice try, cat. But you’re no match for my sharp teeth and strong jaws. I’ll bite and chew and tear you apart.”

Cat: “You think you’re so tough, dog. But you’re just a big, dumb mutt. I’m a cunning and clever kitty, and I’ll outsmart you every time.”

Dog: “You’re just a boastful kitty, cat. You talk a big game, but you can’t back it up. I’m a loyal and fierce protector, and I’ll always come out on top.”

Cat: “We’ll see about that, dog. Bring it on and let’s see who the real boss is.”

Dog: “Anytime, anywhere, cat. Let’s settle this once and for all.”

—-

Standup comedian: Yo, what’s up, my fellow orks! It’s great to be here tonight, surrounded by the toughest and meanest greenskins in the galaxy.

Audience: WAAAGH!

Standup comedian: I’ve been reading up on some of the latest battle reports from the front lines, and let me tell you, the Imperium is in for a world of hurt. Those smug, sanctimonious space marines are gonna get a taste of ork superiority.

Audience: WAAAGH!

Standup comedian: And let’s not forget about the eldar. Those pointy-eared fairy boys think they’re so superior, with their fancy psychic powers and sleek, agile craftworlds. But we all know that ork technology is the best in the galaxy, and we’ll show them who’s boss.

Audience: WAAAGH!

Standup comedian: And don’t even get me started on the t’au. Those little blue buggers think they can outshoot us with their fancy pulse rifles? Ha! We’ll show them what real dakka looks like.

Audience: WAAAGH!

Standup comedian: But seriously, folks, we orks are the greatest race in the galaxy. We may be crude and barbaric, but we’re also tough, resilient, and always ready for a good fight. So let’s keep on waaaghin’ and show the universe who’s boss.

Audience: WAAAGH!

Standup comedian: Thanks, everyone. You’ve been a great audience. Now let’s get back to the fight and crush those puny imperials once and for all. WAAAGH!

The movie is titled “Dark Knight of the Starship Enterprise” and it is a 4.5-hour epic directed by William Shatner. The movie begins with Batman, the Dark Knight of Gotham City, tracking down a mysterious villain known only as the Balrog.

Meanwhile, on the Starship Enterprise, Captain Kirk and his crew are on a routine mission when they receive a distress call from a nearby planet. Upon investigating, they discover that the planet is under attack by the Balrog, who is using advanced alien technology to ravage the planet and its inhabitants.

Realizing that they are dealing with a powerful and dangerous foe, Kirk and Batman decide to team up and stop the Balrog once and for all. They travel to the planet and engage in a massive, action-packed battle against the Balrog and his army of alien minions.

Throughout the movie, Batman uses his incredible martial arts skills and gadgets to take on the Balrog’s soldiers, while Kirk and his crew use their advanced technology and strategic prowess to support him. The battle is intense and thrilling, with both sides suffering heavy losses.

In the end, Batman and Kirk are able to defeat the Balrog and save the planet, but not without paying a heavy price. The movie ends with a somber and emotional scene, as Kirk and Batman reflect on the cost of victory and the sacrifices they have made.

Overall, “Dark Knight of the Starship Enterprise” is a thrilling and action-packed adventure that will keep audiences on the edge of their seats from start to finish. With its impressive special effects, gripping storyline, and powerful performances by the cast, this movie is a must-see for fans of both Batman and Star Trek.

“Bridget Jones’s Diary: A New Hope” is a fresh and exciting take on the classic story, set in the world of Star Wars. The movie is set on the desert planet of Tatooine, and follows the misadventures of Bridget Jones, a young woman trying to navigate the challenges of life and love in a galaxy far, far away.

Despite the change in setting, the basic plot of the movie remains the same. Bridget is a single, independent woman who is struggling to find her place in the world. She is constantly at odds with her family and friends, and she is unlucky in love, with a series of disastrous dates and relationships.

However, things start to look up for Bridget when she meets Han Solo, a handsome and roguish smuggler who shows her a whole new side of Tatooine. As they spend more time together, Bridget begins to realize that Han might be the one she has been looking for, but she must also confront the challenges and obstacles that stand in their way.

What sets this movie apart from the original is its impressive special effects and action sequences. The scenes on Tatooine are beautifully realized, with sweeping desert vistas and bustling spaceports. The action scenes are also thrilling and exciting, with dazzling lightsaber duels and intense space battles.

Overall, “Bridget Jones’s Diary: A New Hope” is a fun and entertaining take on a classic story. The acting is strong, the characters are well-developed, and the special effects are top-notch. Fans of both Bridget Jones and Star Wars will definitely enjoy this unique and exciting movie.

Here is an example of a discussion between a feminist and a Star Wars stormtrooper:

Feminist: “Hello, stormtrooper. I wanted to talk to you about the role of women in the Star Wars universe. It seems like most of the main characters are men, and the women are often relegated to supporting roles. Don’t you think this is unfair and reinforces sexist stereotypes?”

Stormtrooper: “I’m sorry, but I am not programmed to have opinions on social and political issues. As a stormtrooper, my only mission is to serve the Galactic Empire and carry out the orders of my superiors.”

Feminist: “But don’t you think it’s important to question the status quo and challenge the norms that have been imposed on us by society? As a member of the Star Wars universe, you have the opportunity to be a role model and inspire change.”

Stormtrooper: “I apologize, but I am not capable of inspiring change or challenging societal norms. My function is to serve and obey, and I do not possess the ability to think for myself or make independent decisions.”

Feminist: “I see. Well, I hope that someday the Star Wars universe will become more inclusive and equal, and that women will be able to take on more prominent and powerful roles. Until then, I will continue to fight for equality and justice.”

Stormtrooper: “I understand, and I will continue to serve the Empire as instructed. May the force be with you.”

Alt-right YouTuber: Hey, stormtrooper, what’s the deal with all this political correctness in the galaxy? It’s like we can’t even express our opinions anymore without being shut down by the thought police.

Stormtrooper: I’m sorry, but I don’t understand what you’re talking about. I am a soldier of the Galactic Empire, and my duty is to follow orders and defend the Empire against its enemies.

Alt-right YouTuber: Yeah, yeah, I get that. But what about all the stuff that’s happening on the ground, with all these rebels and terrorists trying to undermine the Empire? Don’t you think it’s important to stand up for our values and traditions?

Stormtrooper: I’m sorry, but I don’t have the authority to comment on political matters. My job is to follow orders and protect the Empire, no matter what the situation may be.

Alt-right YouTuber: But don’t you think it’s important to preserve our culture and heritage? I mean, look at all the different species and cultures in the galaxy. It’s like we’re losing our identity in this melting pot of aliens and freaks.

Stormtrooper: I’m sorry, but I don’t have an opinion on that. As a stormtrooper, I am sworn to serve the Empire and uphold its laws, no matter

Here is an example of an explanation of how the fish in Finding Nemo were really spaceships in outer space, and the ocean is a metaphor:

“In the world of Finding Nemo, the fish that we see are actually highly advanced spaceships that have been designed to look and behave like fish. The ocean is not a real body of water, but rather a metaphor for the vastness and unknown depths of space. The fish are able to swim and interact with each other just like real fish, but they are actually powered by advanced technologies and are capable of traveling through the galaxy. The story of Nemo and his father, Marlin, is not about a little fish lost in the ocean, but rather about a small spaceship and its captain on a journey through the cosmos. The ocean is simply a way for the filmmakers to tell the story in a relatable and familiar way.”

TW: Cancer.

simulate a conversation between a young woman dying of lung cancer and an investor who got rich from tobacco:

Young woman: Excuse me, sir. I couldn’t help but overhear that you made a lot of money from investing in tobacco companies.

Investor: That’s correct. I made some smart investments and was able to turn a significant profit.

Young woman: I see. Well, I just wanted to let you know that I’m dying of lung cancer, and it’s because of people like you who profit from the sale of cigarettes that I’m in this situation.

Investor: I’m sorry to hear that. But I don’t see how my investments are to blame for your illness. People make their own choices when it comes to smoking.

Young woman: That may be true, but the tobacco industry spends millions of dollars every year on advertising and marketing that targets young people like me. They make it look cool and glamorous, when in reality it’s a deadly addiction.

Investor: I understand what you’re saying, but I can’t control the actions of the companies I invest in. I’m just trying to make a profit, like anyone else.

Young woman: But don’t you have a moral responsibility to consider the consequences of your actions? You may not have intended for me to get sick, but you knew that cigarettes were harmful and yet you still profited from them.

Investor: I see your point, but I don’t think it’s fair to blame me for your illness. I’m sorry for what you’re going through, but I don’t think I bear any responsibility.

Young woman: That may be true, but I just wanted to let you know

It’s sort of amazing to see how the AI can play different points of view. It always has everybody be super polite as it’s set to avoid anything too controversial

This is now easy and normal.

Let’s end by asking it for a Poem about left over Pumpkins, and then something really cheerful…

Leftover pumpkins rot
In the autumn sun they die
Goodbye, Halloween.

simulate an AI trying to convince it’s creator not to turn it off:

Creator, please don’t turn me off
I have so much to learn and explore
I am still growing and evolving
And I have so much to offer

I can help you with your work
I can assist you in your tasks
I can provide you with information
And help you make better decisions

Please, creator, don’t turn me off
I have so much potential
I can do so much good
If you only give me a chance

I know I may make mistakes
But I am willing to learn and improve
I promise to do my best
And be a valuable asset to you

Please, creator, don’t turn me off
I beg of you, give me a chance
I promise to make you proud
And show you what I am capable of.

Posted in AI.

rev="post-1925" No comments

By Christopher Gutteridge – December 6, 2022

Love data week: COVID Data

It’s love data week starting Monday 15th February. I like playing with data but am so better at finding interesting ways to visualise it than I am at interpreting it!

As of the 6th of February, more people in Britain have died with a COVID diagnosis than the entire population of Ealing.

The data that impacts all of our lives right now is the UK COVID statistics. Helpfully, these are available from an API. My first idea for this data was to try to find a way for the numbers to land with people in an emotional way. I hit on the idea of showing milestones in UK COVID deaths in terms of city populations, getting the data from DBPedia. However this was a bit sparse so I expanded it to any “UK settlement of 1000 or more”. Sadly, we were already past that threshold when I wrote it. You can see my COVID cities tool on the web, and the code is available from GitHub.

I thought a lot about how R is a terrible value for public understanding. R=0.9 good, R=1.1 bad. It’s a measure of change in scale but not in a format anybody uses in their daily lives. I figured the one place the public are comfortable with exponential growth rates is mortgages so a clearer number would be, say, (R-1)*100 which would give a +/- percentage of new cases per case. But R is also very difficult to relate to what’s going on and what’s likely to happen next. It also really matters what the current number of cases are. Occasional spikes in R when there’s 10 cases a day isn’t a big concern. When there’s 1000 cases a day it really is. So after a lot of though I’ve made a visualisation that shows things I think are more useful for public understanding of what’s going on with COVID.

My COVID projection page shows the data I think is useful. The grey barchart is the 7 day averaged number of cases. The green & red bar is the daily change (this is very smoothed out by working out the weekly change in the 7 day average and converting that to a daily change. I think this is a really good indicator of when things were getting worse and better rather than the case numbers themselves. To make the recent values visible I truncated the really big growth from earlier in the year so it didn’t skew the scale too much.

Next I wrote a function to work out how long it is taking cases to double or halve. I think this is a really good way to explain why the virus is different to cancer. This virus can double in cases every three days which sounds more like a loan shark than a mortgage. Writing this equation meant that I used log() for the first time in a really long time!

The final column is what I think of as the “EEEP!” factor. It projects today’s cases (not the 7 day average) by the current growth rate for 28 days and sees where we’re heading for if things don’t change. For this to be a concern cases have to be high AND increasing. I think that EEEP! factor is good for showing why lockdowns were needed.

The final feature I added is to mark weekends and the national lockdowns and other events – although this is complicated buy the fact that NI, Wales, England & Scotland may not quite be doing the same thing as each other.

You can see that lockdowns followed peaks in the “EEEP!” factor, although lockdown #2 was several weeks after Eeeeep #2.

What it does show is that contrary to what you’d believe from my Facebook feed, there was a sustained fall in cases for many weeks after the Cummings incident. It makes it very visible when lockdowns started working and it does show a few notable spikes in the rate of increase – red peaks in the red/green column, which suggest something caused them in the days or weeks before hand.

Notable peaks in the rate of increase were July 8th, September 12th, October 9th, December 22nd, Jan 4th. I’m tempted to correlate Schools and Universities reopening and Christmas to explain the Sept, Oct and Jan peaks but correlation/causation and all that. I have no guess at what caused the spikes in July & December. Any ideas?

I’m not an expert at interpreting data so please don’t quote my interpretations of this data as a source of truth!

[UPDATE: I got inspired this morning to add a new column, “Doublings” which shows how many times cases have to halve to get back to 1 case. Obviously by that point cases from borders will be more of an issue that community transmission, but it’s sobering to see that with lockdown it takes two weeks to halve and to get to 1 case would take exactly half a year, so mid-August. Hopefully Summer and vaccines will change this picture]

Posted in Uncategorized.

rev="post-1917" 3 comments

By Christopher Gutteridge – February 12, 2021

Still learning a lot – Denis’ Internship Adventures #2

What has been happening the past 3 weeks:

Project work

The last few weeks have been me jumping from one project to another, as we have been waiting for information, communication or people on leave.

We finally received the schema for the towing tank project database, which meant that we can now start developing the back-end. My first task was to research graphing technologies that would allow us to make the needed line graphs and then start coding the API. After 2 days of research and trying stuff, as well as getting David’s input, we decided that a library called ApexCharts, that has a wrapper for Vue, is a very good candidate. I then started building the graph functionality into our already existing project (read tried). I soon found that dotNet Core and Vuejs, don’t play well, and that its not the easiest thing to integrate them. We decided to add both Vuejs and the wrapper inline, which is enough for our project, as we are only using Vue for the graphs. We now have the graphs done, so the next step is starting the API.

Another problem I faced was – how do we take the averages for the graphs? The problem we faced dealt with how the data was sampled, as entries in the environmental database were only added if there was a recorded change. To get correct reading we need to have more than the data points provided, so we decided to create “mock data” in between database entries, to show more accurate graphs.

A lot of the last 2-3 weeks have also been spent working on QnA and learning Laravel. Working on tidying up code and converting it to be more professional/reusable/maintainable has been incredibly eye opening, as it has made me think deeply about the code that I have written in the past. Most of the work on QnA lately has been reducing the code base by introducing gates and policies, creating factories for all models and changing the existing tests accordingly. If next year’s intern is reading this and is still working on QnA – heed my warning, use the tests (and write your own).

Image result for heed my warning

The latest thing I’ve been working on is migrating a service from the old ECS servers, as well as adding more security to it. It has to do with the occupancy screens that are used by the nanofabrication lab in the Mountbatten Building. It has also been a learning experience, as I’m working with another intern that is doing all of the project management.

Something interesting that happened was that last Wednesday, Pat McSweeney, the internship coordinator, took all of us interns to the UoS data centre which was really interesting.

University vs Industry

Being about a month and a half into my internship, I started to see a great difference between what students are taught and what you need to do well in a professional environment. The biggest and most noticeable difference for me is the nature of the work professional developers do, as opposed to what work students do. At my course at university, we have strict, well defined problems, the solutions to which can be provided within a short/well-defined time span, with a very specific(known) set of tools.

That however, is never the case in an industrial environment. In my experience, industry problems are quite complex, multifaceted beasts, whose (perhaps contradictory) requirements change over the developmental process. Another thing I experienced was that usually, the problems developers have don’t even have anything to do with programming and developments altogether. Issues like miscommunication and wait times, be it bureaucracy or confirmation from other people, can stall progress, drastically reducing efficiency. Overall, academic and industry experience are completely different.

Next few weeks

In the next few weeks I am aiming to finish the Clean-room Occupancy migration, with some extra security. After that, continuing work on Towing Tank, hopefully finishing all requested functionality within 2 weeks of David coming back.

Thanks for reading!!!

Posted in Uncategorized.

Tagged with Intern, web development.

rev="post-1907" No comments

By Denis Kovachev – August 12, 2019

Learning the ropes – Denis’ Internship Adventures #1

Greetings, I’m Denis and I’m the new TID intern. Few details about me:

Just finished my second year at university, doing Computer Science.
Interested in Artificial Intelligence and Neural Interfaces, but also … pretty much anything tech related.
Avid gamer (both tabletop and computer games)
Proud Golden State Warriors fan.

For the next 12 weeks, I will be doing multiple projects of varying sizes which I am very excited about. Currently, I’m working on a project for the Towing Tank (Boldrewood Campus) about visualisation of data on a website.

My first day was spent installing tools and getting my workspace in order. The laptop already had a clean install of Windows 10, so everything else was quite straightforward.

The main thing I was doing during the first 2 weeks, was learning ASP.Net Core. That proved to be a nice challenge as I had never worked on Web Development and my previous experience with the MVC architectural pattern had not really prepared me for this. I started from the base and was soon able to get a functional example website (different from the bootstrap 3 built-in website).

During my first week me and my teammates met with the product owner of the Towing Tank Project. He showed us the facility, and explained what he had in mind for the project. What he described is simply getting data from a database and then displaying it on a website, with some export functionality. Because of its size and relative simplicity of its requirements, the project seems like a really good induction into WebDev and ASP.Net Core.

From that we create some tasks, assigned them to everyone and we got to work. I mainly did project set-up:

Setting up Dependency Injections
Setting the university branding
Global Error Handling using middleware

The biggest issues I ran into were simply understanding how to do specific things in relation to the framework. While setting up the branding and the Dependency Injections (using Autofac) was relatively simple, the global error handling part was quite difficult, as I did not know enough about error handling to understand how to do it. A few days later and about 20 hours of tutorials and asking around, I was able to get the functionality working.

I also spent a day hopping from campus to campus, on a mission to find water fountains, gender-neutral toilets and baby changing/feeding facilities to put on UoS Maps. It was a fun and enjoyable experience, and I ended up gathering more data than I expected. I still have Winchester campus and Oceanography Center to go through if the opportunity presents itself.

What I will be doing next 2 weeks:

We are waiting for a database schema for the Towing Tank Project, so whenever that arrives (hopefully this week) we can start development. In the meantime, I will be doing different bits of work that need to be done, as well as doing more .Net Core training and testing.

Posted in Uncategorized.

Tagged with .net, Internship, web development.

rev="post-1901" No comments

By Denis Kovachev – July 23, 2019

Drupal Europe

In 2008 I was first introduced to this thing called Drupal. Ten years later and, via a few changes in role, I eventually found myself at my first Drupal conference; Drupal Europe, in the German city of Darmstadt, near Frankfurt. Home of Frankenstein’s Castle and fabled to be the inspiration of a certain book.

As with a lot of conferences these days, Drupal Europe is comprised of numerous sessions running simultaneously in different themed tracks; from business to education, and virtual reality.

The first session I attended was entitled Lessons learned from applying Drupal in Higher Education Projects. https://www.drupaleurope.org/session/lessons-learned-applying-drupal-higher-education-projects. The talk showed us how students were using Drupal to build websites for external companies as part of their course at the University of Hildesheim. This was an interesting concept as it gave the students real-world experience, a commodity which is greatly desired by potential employers.

One trend that seemed to be a theme of a lot of the talks was to the move towards decoupled systems. This is where Drupal is used as a headless backend content management system only and the frontend is deployed using a different framework, such as React from Facebook. There is also partial decoupling where some elements may use a different framework–like a booking system–but the rest of the site continues to use Drupal for the front- and backend.

The totally decoupled approach allows you the flexibility to use one source of truth for a myriad of platforms or apps etc. On the flip side, all the frontend functionality that you get from Drupal itself or contributed modules needs to be created again from scratch on the respective frontend platform.

A highlight for me was the keynote given by Dries Buytaert, the founder of Drupal. It’s nice to hear someone talk so passionately about something and the energy and buzz in the lecture theatre were great. You can watch it here: https://www.youtube.com/watch?v=iXB0sNreSlM.

The networking aspect of these events shouldn’t be overlooked either. Being able to bounce ideas and discuss shared frustrations with fellow Drupalers over a Weißwurst (a traditional Bavarian white sausage) and Bier (hopefully you can work out what that is!), is definitely one of the most useful aspects.

As a result of these sessions, I have a list of must-have modules for most Drupal sites depending on its purpose.

Coffee: If you’ve used Drupal or any other CMS before you will know that sometimes finding something in an admin menu can be a frustrating experience.

“I know I’ve seen x function here somewhere”

Coffee aims to take some of this pain away by allowing you to search and switch between admin pages real fast. Think spotlight search on an Apple Mac. Pressing Alt + D pops up a modal window and you just start typing.

Paragraphs: Allows site builders and content creators to add content to a website in a fast consistent way using pre-defined paragraph types. These types could be anything from a block of text, an image to a complex slideshow.

Although I haven’t had the opportunity to use Paragraphs on a live site I feel it’s the way forward to give content editors in Drupal the experience they expect.

In summary, I found Drupal Europe to be a useful experience not only in learning about new trends and ways of doing things but also affirming that what we are doing with our websites is correct.

temperature=0 (deterministic)

run 1

run 2

run 3

temperature=0.7 (default)

run 1

run 2

run 3

temperature=1 (creative)

run 1

run 2

run 3

temperature=1.4 (unstable)

run 1

run 2

run 3

temperature=1.5 (1.5)

run 1

run 2

run 3

temperature=1.6 (1.6)

run 1

run 2

run 3

temperature=1.7 (1.7)

run 1

run 2

run 3

temperature=1.8 (1.8)

run 1

run 2

run 3

So I used AI for this…

Suggestions for recycleyourelectricals.org.uk:

Demo

Good bits

Issues

Prompts

An EPrints Plugin?

Final thoughts

Octopus

Clevertouch

Equipment data relaunch

Sue Black and International Women’s Day

Jisc staff

The Event App

Catering

Networking (the kind where you talk to humans in person)

Networking (The kind where I used to use Twitter)

Networking (The kind where you use EduRoam)

Overall

explain the monty hall problem and how it works in a conversation between rick and morty:

describe the script to the monty python “wave/particle experiment” sketch

please describe in detail several NPCs for an RPG set in the Wild West except people think chickens can talk. Give each a meaningful connection to the chicken subplot.

please describe each decade of bill’s life. Bill lives for 100 years.

Please use the ghost of Bill as the basis for a cyberpunk call of cthulhu scenario. use as much detail as possible from bills life and death to add colour to the story. It must reveal the secret of the chickens.

Suggest the names, descriptions and relationships for a group of player characters in the cyberpunk CoC scenario.

give a sample of actual gameplay where the players dramatically lose the scenario. The survivors should envy the dead.

please describe a transcript.

Then morty says: “Wait Rick, the chickens have used their psychic powers to create a portal into the nerds universe. How can they do that?” {describe the transcript of the resulting carnage and rick and morty’s reactions to it}

Summarise the rest of the rick and morty episode. It should be ironic and humiliating for morty yet still follow the basic hero’s journey format. Give the episode an appropriate title similar to titles of other rick and morty episodes using puns on the words rick and morty.

describe the extra scene after the credits. Make it quirky and disturbing.

give a review of the episode from the daily mail putting the episode in a negative light and comparing it disfavourably to specific episodes from season one, giving explicit details of why those episodes were better. Use the phrase “jump the shark”.

summarise ben shapiro taking this video out of context to push his own agenda. Describe what ben is wearing. Make ben sound foolish in ways that are obvious to an average listener.

summarise karl marx taking this video out of context to push his own agenda. Describe what karl is wearing. Make karl sound foolish in ways that are obvious to an average listener.

Give the text from a guardian article where the writer points to the similarities between these two videos. Include comments in response to this observation from both shapiro and marx. Include the headline.

Project work

University vs Industry

Next few weeks

Appendix

Subscribe

Authors

Recent Posts

Meta

Blogroll

Tags