Ever wonder how your favorite streaming service reads your mind and suggests the perfect movie? Or how your phone’s camera can spot your dog in a photo full of cats? That’s not magic, it’s Artificial Intelligence! But ‘AI’ can feel like a complicated, technical term.
Watch
- What is Machine Learning (2 min.)
- Generative AI explained in 2 minutes (2 min.)
To make sense of it, let’s use a metaphor: A futuristic kitchen:
As you can see from the image, each concept in AI builds upon the last. (click on triangle for more details)
The Kitchen (AI) is the whole field, everything related to making machines smart.
AI is the broad field focused on building systems that can perform tasks that typically require human intelligence like recognizing speech, making decisions, or generating content.
The Learning Styles (Machine Learning) are the different ways the kitchen can learn. It can follow a labeled Cookbook (Supervised), organize a messy Pantry on its own (Unsupervised), or learn by trial-and-error like a Robot Chef (Reinforcement).
Machine Learning is one of the main ways we achieve AI. Instead of programmers writing explicit, step-by-step instructions for every single possible situation, ML systems are “trained” to learn from large amounts of data. They identify patterns in the data and use those patterns to make predictions or decisions about new, unseen data. Think about Netflix recommendations or facial recognition on your phone.
The Chef’s Intuition (Deep Learning) is a more advanced technique, using complex ‘neural networks’ to figure out recipes from massive amounts of information, like just looking at a photo of a dish.
Deep Learning is a type of machine learning that uses layered neural networks to process large amounts of data and it’s especially good at handling complex patterns in images, text, or speech
The Food Replicator (Generative AI) is the most revolutionary appliance. Instead of just identifying food, it creates brand new dishes from scratch based on your instructions.
Generative AI refers to AI systems (usually based on deep learning) that can create new content like text, images, music, or video by learning from examples and generating outputs that resemble them.
LLMs are a specific kind of generative AI trained on massive text datasets to predict and generate language in a human-like way. They’re the engines behind tools like ChatGPT and Claude.
Activity
But first, let’s acknowledge we’re using metaphors, like chefs, kitchens, and cookbooks, to help explain AI. Even the title of this lesson “What’s Under the Hood?” is a metaphor. That’s intentional. Generative AI is complex and abstract, and metaphors help us connect abstract concepts to things we already understand.
But here’s the catch:
Metaphors do more than illustrate. They can also frame how we perceive systems, what kinds of questions we ask about them, and what we assume they can (or should) do.
Saying “AI understands you” or “the model is a chef” or that we can “see under the hood” can be helpful, but it can also be misleading. These systems don’t understand, plan, or think the way people do. And they aren’t mechanical like a car engine, they are mathematical. They generate responses by predicting what’s likely to come next based on patterns in massive datasets, not lived experience or reasoning.
When it comes to generative AI discourse, there’s a fair amount of metaphor that can shape our expectations about it. Stay curious and ask:
“What does this metaphor help me see more clearly?”
“And what might it oversimplify or obscure?”
- Visit ChatGPT. If you already have an account, great, but you can use ChatGPT for this activity without signing up. Type the following prompts in the “ask anything” text box:
- Prompt 1: “Give me a recipe for a dish that symbolizes resilience”
- Prompt 2: “What would the same recipe look like if it was written by a homesick astronaut?”
- Prompt 3: “Now rewrite that as if the dish is a conversation between ingredients”
Discussion
After using ChatGPT, how did your expectations going in shape the way you interpreted its response? Did the output feel better or worse than you anticipated? Were you surprised, disappointed, impressed? Why?
64 replies on “thing 2: AI 101: What’s Under the Hood? ”
This was fun! I did enjoy the outcomes, especially since I didn’t know what to expect. The last prompt turned out to be really enjoyable especially with the ‘dialog’ between the ingredients also noting their emotions as they ‘spoke’. It is interesting to see how each outcome resulted from the prompts given.
Interesting and impressive!
Wow! The ChatGPT exercise was crazy. Very creative. I could not have come up with anything like that. I wonder if ChatGPT’s responses were the same for each of us when using identical prompts? If not, were they similar?
I’m not sure what I expected with these prompts. The first prompt definitely gave me something that was easy to read and usable. The second and third prompt seemed a little ridiculous to me, and I was surprised at how fast I got results and how thorough they were. I’ve never considered having ingredients in a recipe have a conversation and I’m not sure that I need to! But I can see this being a valuable creative tool.
The three vegetable are the three main agricultural crops of various indigenous people of Central and North America: squash, corn and bean. And they are a complete meal with protein, carbs and the vitamins. Thus, this is a metaphor for sustenance and balanced nutrition, resilience because these items together fed the community, , culture as it is passed down… I think we got the results so quickly because so many people were asking the same thing. I did appreciate where it stated: we are more than the sum of our parts and I am resilience served warm.
When I first read the prompt I thought it would give me a recipe for a food that is hard to damage or can survive in different conditions. What I was actually given was a recipe for “Three Sisters Stew”, which is created with three plants that are planted together and help each other grow. I thought it was an interesting interpretation of “resilience”. I was impressed the second prompt changed all of the measurements from tablespoons and cups to packets, cubes, and pouches like they would actually have in space.
I was surprised by how the language returned by these prompts reflected patterns I see most in quickly produced internet content. The second prompt returned a script that read like a TikTok video, and the third used parenthetical adverbs/descriptions in a way that was popularized by instant messaging conversations. The content read clean and tight, but shallow.
This exercise was very interesting. It seems we all got different recipes (mine was Braised Lentils with Roasted Root Vegetables & Herbed Yogurt) based on our past search history possibly? The reasoning for the recipe was solid. After the second prompt it turned into “Starboard Lentil Stew with Roasted Root Veg & Zero-G Yogurt Swirl
Captain’s comfort food log, Sol Cycle 84” – which was super fun with the comments added in and language changes in the preparation guide. The third prompt (A Conversation in the Pot: The Story of Resilience) made this just hilarious and entertaining!
This exercise highlights the creative abilities of generative AI. I did not expect the responses to be so descriptive and nuanced. From that vantage point, the responses impressed me. Makes me wonder if any of us will actually create one of these concoctions.
It wouldn’t let me use ChatGPT in a private window without logging in, so I had to use a regular browser window. It gave me a pretty solid beef stew recipe, and then had a section after the recipe where it went through the symbolism for the choices. It generated a lot of text for all three answers very quickly. It asked for feedback each time in a whimsical way, which matched the whimsy of the prompts. It wouldn’t be how I want to look for a recipe, but could be fun for idea generation.
WOW! impressive, the third prompt was amazing, I really enjoyed the poem at the end. Even the second prompt was great. It is a little scary but interesting and fun!
Since I am not unfamiliar with ChatGPT, these responses were very much in line with the expectations I had going into the activity. While the prompts are not the typical things that I would refer to the system for, the length and floweriness of the responses, especially the first two, were consistent in style with responses I am familiar with ChatGPT giving out. I was a little surprised by the brevity of the last response, as mine gave me little blurbs from each ingredient that was more like mini monologues rather than a conversation amongst them. I am curious about what made it give us different initial recipes (if using it as a guest instead of in an account). Mine was “Braised Lentils with Roasted Root Vegetables.”
That was a fun exercise. The answers were creative and interesting. I wasn’t expecting to receive something so imaginative from an AI program.
I have used ChatGPT before, but not in such a creative sense, more for practical means. I first prompt response was about what I expected. I thought it was interesting how it could change the recipe’s backstory based on perspective and even make the ingredients converse with each other. Very creative!
The Chat GPT replies were about at the level I expected. “What under the hood” topic title was somewhat misleading. I don’t think we really learned what’s under the hood. 🙂
This was fun. I was impressed with the recipe and surprised by the creativity of the answer to the second prompt. I read it thinking the answers would be cliche and obviously AI generated. In a way this actually makes me more skeptical of the benefits of generative AI to our society.
I thought these ChatGPT prompts were really interesting and creative. I wonder how our students would respond to such creative prompts if this were a human writing exercise. ChatGPT gave me a recipe for Three Sisters Stew and did a good job of rewriting the recipe from a homesick astronaut and creating a dialog between ingredients. ChatGPT also offered to create a mission patch or to reformat the dialog as a script for use in a children’s classroom– trying to guess what else I would use such a thing for. In general, I don’t think ChatGPT does a bad job at things like this– using genre and creative writing, generating images, reformatting text– but my preconception remains that it is really sad to outsource our creativity and let ChatGPT have all the fun of doing the imagination work. A lot of people using ChatGPT with the same prompts will get some variety, but in general, I think it flattens possibilities. For example, for the first prompt, it seems like we all got similar recipes. If the prompt for an in class writing was “Describe a dish that reminds you of home,” we would have a wider array of descriptions and recipes and so many more possibilities for the next prompts, using human imagination (and ideally having fun doing it).
Talk about a good time. I received similar stylist framework responses, except instead of getting the root vegetable suggestion, I was prompted with stone soup. I have been a paying subscriber to ChatGPT since March of 2025. It knows me, so to tell me to make a soup with a stone (other veggies suggested) is very me. When I entered in Prompt #2 it did the same formatting and added a flavor (See what I did there) into the language “Mission Day Log” and a lot of freeze dried ingredients and even titled the ingredients section (Ingredients: Memories of Them). Now prompt #3, I agree with alblazer. The AI keeps telling me it’s just a mirror and the sassy salt and prickly pepper ingredients are just echoes of an echo from a source which stopped making noise long ago. Excellent exercise if you have not used ChatGPT before. Note: No stones or vegetables were harmed nor was AI used in the production of this comment.
Very interesting. I was really impressed by the recipe and the subsequent iterations of the question. I actually thought I might like to try the recipe (lentils and roasted root vegetables) – sounded unexpectedly delicious!
The different responses in ChatGPT were definitely entertaining. It was better than I had anticipated it being. The last one with the conversation between the ingredients was really fun. The recipe sounds really good too, so that’s a bonus.
I enjoyed the recipe and then the translation from an astronaut, but I did notice that in the last version there were no specific measurements which is surprising since it was supposed to be based on a recipe and measurements are important.
I didn’t really expect what AI came up with, Resilience Stew, which actually sounded very tasty. With the first prompt it gave the recipe with the ingredients being a variety of root vegetables and spices which made me think I may not have a lot, but I have what I need. The second prompt the stew had a different name Smoky Root Stew symbolizing a comfort food from childhood possibly and the Astro naught wanted something that took him back to the comforts of home in his mind. The third was rather enjoyable as the strengths of each vegetable came through in their character individually but then they all came together and described what each one brought to the stew to make it a perfect meal. Amazing how each stew gave you a different view of what resilience looks like.
My recipe was Braised Root Vegetable Stew with Lentils, which turned to EARTH STEW — Makeshift Memory Ration in the second response. The ingredients made me chuckle, especially the broth base (filtered greywater + bouillon cube) and wilted kale scraps from hydroponics deck. ChatGPT offered to make an audiobook from it, or a children’s picture book. Interesting experiment!
I was really tickled by ChatGPT’s interpretation of “Now rewrite that as if the dish is a conversation between ingredients.” It made it into a little play and gave each root vegetable its own personality. I didn’t expect it to write a whole script!
However, while reading the astronaut log and the script, I’m wondering how ChatGPT will shape our language, e.g., the excessive (and often times inappropriate) use of the em dash. Will younger generations pick up on it and normalize its use? Will ChatGPT reinforce “bad” or unorthodox spellings, like “payed” vs. “paid”?
I too had to learn what an em dash was. I struggle with the question can machines create art. What if a machine a human created, created another machine to create art. When I write poetry or songs and I intentionally misspell the phrase “Imma git pyd!” (I am going to get paid!) as a play on the complexity of the English language but ChatGPT keeps trying to correct my spelling.
I got a cassoulet. I too was entertained with the outcomes. At the end I added a fourth prompt “critique this conversation like a literature professor would.” It’s critique was just as long as the conversation itself and it gave itself a B+.
This was a fun exercise, and I tried different prompts as well to see what the results were. Instead of resilience, I asked to write a dish that represents a Broadway musical
It would be interesting to see how, if at all, a response might evolve over time even with the same prompts.
Lately, I’ve been using MS CoPilot for writing narratives. I enjoy giving it a starting point and asking it to refine it in different ways until I get exactly the wording I was looking for but unable to attain with my own brain power. The exercise was eye-opening in that AI can be utilized in so many different ways and generate so many curated or customized results!
My pot boil-ith over – what a hoot! I needed that after stressing with workday ALL day! I took ChatGPT’s suggestion and had it convert my recipe into a vegetarian dish, then followed w/ 2+ 3 prompts. Definitely creative, not what I expected. Maybe it had a few too many wild mushrooms before adding them to my pot? Excited for thing #3 already.
Based on a few favorable ChatGPT comments from friends who have used it, I expected nuanced responses to the three prompts. The output was funnier than I expected. I am wondering if I got a vegetarian recipe because the last person to ask influenced what foods the AI interpreted as resilient?
Having used ChatGPT for a multitude of prompts, including a very cute one of my dog in W&M gear, I enjoy its practical and “creative” answers. My meal was Braised Lentil & Root Vegetable Stew with Lemon-Herb Gremolata. I have a subscription, and have used this to meal plan a bit. I’m pretty confident it gave me a vegetarian answer at least partly because it knows I ask it for vegetarian meals.
However, the last dialogue was highly amusing – “Here’s the Braised Lentil & Root Vegetable Stew rewritten as if the ingredients are having a conversation, like they’re in group therapy for resilience”. I’m not sure why it framed it like group therapy, but it was very interesting.
In terms of feeling certain ways by the output, I’ve realized that going in with vague prompts will lead to outputs you may not exactly want, so I was not anticipating anything in particular for a reply. For example, my astronaut was in zero gravity, but if I wanted one on a space station that needed to be specified. If you have an idea of a specific type of output you need to be specific with your input.
I’m so intrigued at how many different recipes came out of the exact same prompt! This is the kind of prompt I find chatGPT very useful for because it gives a really creative launching pad for ideas.
This exercise was surprisingly delightful! When I think of “machine learning”, it connotes something cold and sterile to me. But the creativity of the prompts and the responses made me smile. I tend towards a cautious view of AI and the risks, and even the metaphors that anthropomorphize chatbots concern me. So the warmth of the responses caught me off guard in a good way.
I was impressed with the speed and creativity. I find it interesting that many of us saw similar responses. So I asked why? (I still have trust issues regarding current and potential uses.) Answer:
“When I get the same prompt from multiple users, I generate each response independently, in real time, for that specific conversation. I don’t reuse or copy past responses because:
No shared memory between users – I don’t know what I wrote for anyone else. Every chat is private and separate.
Context matters – I adapt the tone, style, or details based on your previous messages, preferences, or how you’re interacting with me.
Creativity is dynamic – Even if two people ask for “a recipe that symbolizes resilience,” I might offer different dishes or creative takes each time because I have multiple ways to express the idea.
Think of it like a chef improvising—same ingredients, but each meal is cooked fresh.”
I wasn’t sure how the responses would go but they were interesting. I think the interpretation of a word is just that and to have picked that ingredient was curious. The second prompt was somewhat strange but given the prompt, it did the job. I think by the third prompt I felt somewhat entertained but question whether I would be looking for material to assist me if I was not quite comfortable with the subject matter and cautious with my prompt.
The first recipe read like anything you’d see if you googled a recipe and were reading from a summary and not someone’s page, generic and straightforward. I thought it was interesting that with the astronaut, it added humor and sarcasm mimicking how it thinks an astronaut would feel; I was surprised at the vernacular, “Okay, they’re rehydrated or printed – but memory does the rest”…it’s very human. But I also saw things that the AI added that are kind of weird, like theming the recipe to be space-oriented, titling parts of the recipe as The Steady Orbit and The Survivors, and The Soft Landing, which feels not-human. The final piece was cute and felt like a satire written by a favorite author. I don’t know why I felt that way about the vegetables talking to each other and not the astronaut writing out a recipe.
I received a recipe for a basic lentil stew. The subsequent prompts gave me rather corny results, with the astronaut commenting out each ingredient with words of longing for home, and the ingredients didn’t so much talk together as expound on what they brought to the dish. The results were interesting, but felt at the level of a 3rd grade writing assignment. What I think it more interesting is the range of recipes that the identical prompt served up for different users. I wonder how often it repeats itself.
Interesting. The first was a typical recipe with story found online. The astronaut and ingredients read more like a short story in a comical way.
I was surprised and slightly amused. I felt the need to research how astronauts actually eat in space and wondered if their food would fly around in zero gravity. Apparently, if they are careful, it does not. I enjoyed the “conversation” among the ingredients as it shed light on the perspective of each.
It’s interesting to read the comments and hear how different individuals got different results (but a lot of the recipes were stews). It impressed me that ChatGPT was able to come up with responses that made sense for the last two off-the-wall prompts. I get the sense that a lot of using AI effectively is going to center around the best prompts to use. One thing that didn’t surprise me was the tone/voice/writing style of the response, which I’ve come to recognize in other summaries and responses generated by AI I’ve seen online.
I disobeyed a little, I actually fed the prompt to both ChatGPT and Anthropic’s Claude. I was pleasantly surprised by Claude’s outputs, and interested the differences.
ChatGPT gave me a recipe for Cassoulet, ” dish that symbolizes resilience should reflect strength through adversity—something humble yet rich, forged through time and perseverance. One such dish is Cassoulet, a rustic French stew rooted in peasant tradition, originally made with whatever was on hand. It’s slow-cooked, hearty, and evolved through centuries of hardship, wars, and food scarcity.”
Claude gave me sourdough, “Sourdough bread is the perfect metaphor for resilience. The starter is a living culture that survives through feeding and neglect, grows stronger over time, and can be passed down through generations. The bread-making process itself requires patience through long fermentation, adaptation to changing conditions, and the understanding that the best results come from time and gentle persistence rather than force.
The act of scoring the dough before baking is particularly symbolic – these deliberate cuts prevent the bread from bursting randomly and instead create beautiful patterns as the bread expands. It’s a reminder that acknowledging our vulnerable points and creating space for growth actually makes us stronger and more beautiful.
Every baker’s sourdough tastes different because it’s shaped by their environment, their care, and their unique approach – much like how each person’s resilience is forged by their individual experiences and circumstances.”
With the follow-up prompts, I was also pretty surprised how much Claude emphasized humanistic elements and appealed to a very 2025 individualism– references to poetry, longing, it seems to be suggesting that it too goes to therapy.
The conversation was interpreted as a 12 act play, which was a bit overwrought but seems like a credible theater in the park production:
“Act IX: The Scoring
SHARP KNIFE (entering dramatically): “I come not to harm, but to help. These cuts will guide your expansion, make your growth beautiful.”
BREAD FLOUR: “It’s frightening, but… I understand. Controlled vulnerability is strength.”
Act X: The Fire
OVEN (ancient, wise, hot): “Enter, my friends. Here you become what you were always meant to be.”
WATER (as steam): “I protect you in these first moments, keeping you moist as the heat builds your crust.”
ALL INGREDIENTS (transforming): “We are no longer separate. We are bread. We are nourishment. We are the alchemy of time and heat and care.”
It is interesting that we got different recipes for the first prompt. I’m curious to how/why it gives different recipes with the same prompt. Mine was Hearty Lentil Stew with Root Vegetables and Kale. I did like the exercise as it showed how you can get creative, rather than to just use in a more serious way. Fun exercise!
Wow! Really interesting and impressive! Truthfully, I wasn’t sure what to expect, but I was very surprised the by the results.
I was very surprised by the output! The prompts allowed the tool to generate some really creative content. This is quite scary for me as someone invested in the arts. I see how this can be fun, but it scary to think about what this means for creative careers.
I believe I received the same response as a few others. I received the basic lentil stew recipe, and much like Icmorales post it provided a 3rd grade level story. I can see why authors are utilizing GenAI for storyboards and outlines.
I received the similar Lentil recipe as others, (‘Braised Root Vegetable Stew with Lentils and Herbs’) and enjoyed the whimsy in the first in second prompts. Output was about what I expected for prompts 1 and 2, but the story for prompt 3 was ridiculous, I was disappointed in the quality of that response. I can see how the different perspective taking between prompts 2 and 3 could be helpful.
This is difficult to answer because I’ve used ChatGPT for over 2 years now. I think these cute exercises can be fun. I like how the astronaut explained how they would source the ingredients in space and how they related their experience with resilience to the ingredients in the recipe: “Up here, resilience isn’t just about surviving. It’s about remembering—what we came from, what we long for, and how we carry it forward, even when we’re orbiting 250 miles above the soil.” (Although I think it’d be better if the altitude was given in nautical miles or kilometers.) I was actually inspired by this and asked for a story where the lentils and root vegetables had a falling out which let to the root vegetables being forsaken to the ground to never see the light of day again. But then somehow, someway, they were able to overcome their differences and become the dish of resilience again. The story was very interesting! Here are some highlights: “This gospel of forgiveness and flavor spread among the root vegetables. But the Lentils, fearing dilution of their tradition, forced the root vegetables deeper underground—into darkness, into silence.” But “what if we weren’t meant to fight? What if stew… needs us both?” And finally “All ingredients must go into one pot. Not to erase difference, but to balance it. Lentils bring structure. Roots bring sweetness and soul.”
The speed and polish of the ChatGPT responses were crazy! And it was definitely fun to read them, but there’s a missing ingredient (pun intended). To me, the AI products have a generic feeling. Like marketing materials. I think the tool is useful to give a starting point (so much, so fast!), but maybe a human is needed to infuse AI responses with specificity, a singular viewpoint, a real personality, whatever it is that makes us feel a person is there somewhere communicating with us, wanting to feed us.
I was expecting mush — but I got something that was responsive to the prompt. For the first inquiry, each main element of the recipe was tied to the “resilience” theme. The homesick astronaut picked a particular sensory experience (smell); in conversation was a script (and ChatGPT volunteered to rewrite it as a Shakespearean scene). So the mashup was much more successful than I thought it would be.
As a semi-frequent ChatGPT user, the responses were expected to me. While I am becoming somewhat desensitized to how quickly and thoroughly ChatGPT can produce a response, I was initially very impressed the first time that I used it.
Interesting prompts! As a frequent ChatGPT user, I’m still always impressed by it’s speed of and it’s seemingly creative responses.
I am genuinely curious to see if this recipe for Resilience Stew (Braised Lentils with Roasted Root Vegetables) is actually any good! It’s crazy how quickly ChatGPT was able to formulate the recipe and also assign meaning to each ingredient that it used (i.e. the root vegetables symbolizing strength beneath the surface and the lentils symbolizing endurance). My astronaut was trying to replicate their grandma’s recipe in zero gravity. It’s wild how creative it got with that prompt as well as the conversation between ingredients.
I’m forever impressed with the things ChatGPT comes up with. I found it interesting that the resilience recipe was Braised Lamb Shanks with Root Vegetables. The explanation for its choices was sound. I wouldn’t have thought of it.
That was a fun exercise! I’ll be making the first recipe, it sounds delicious! I was surprised and amused by the responses. It almost seemed that ChatGPT had fun with it as well, and has a sense of humor (especially with prompts 2 and 3). It is almost like conversing with a person.
The first response was a little disappointing, as I don’t think of resilience with the book “Stone Soup”, but the second and especially the third response were incredibly creative in how it modified the recipe and story based on the prompt. Shows its creativity, though at times can be shallow and needs additional prompts or human editing.
What a fun exercise! I use ChatGPT for practical matters, emails, summaries, etc. The third prompt, demonstrated how to use it in a creative and fun manner.
Based on the prompts we were given, it was actually how I expected the outcome. I did like the personal/human style touch it gave to the final prompt.
That was a fun exercise! My first thought was that next time I have a bunch of ingredients in the fridge that I want to use up, I will type them in and see what happens.
The second and third prompts were totally surprising to me. I would never have thought about a homesick astronaut circling the earth, or veggies as a cast of characters. Definitely outside the box!
Was it a human or ChatGPT who came up with these prompts? The results are interesting. The recipe ChatGPT came up with is too complicated – it is more or less a regular vegetable stew, but with tons of ingredients, and I am not sure all of them are needed. So I am not tempting to try it. It was also amusing that the second prompt output emphasized “astronaut” way more than “homesick”. I was also a bit surprised that it felt like ChatGPT attempts to make it humorous, without been explicitly prompted. So if I want to cook something I would still go with a cookbook, but if I need to make a recipe for amusement only – this is the way to go.
I could not imagine how the recipe would taste, since it utilizes some ingredients that I am not familiar with. The symbolical use of the ingredients chosen were symbolic of survival, hardships, and rebirth.
It’s amazing that enough information has been gathered to be able to generate such unique answers to each request. I was slightly surprised by how robust the answers to prompts 2&3 were. If I put enough prompt tweaks into AI, it generates responses that sound like something I would put together, if I were that eloquent.
It’s amazing that enough information has been gathered to be able to generate such unique answers to each request. I was slightly surprised by how robust the answers to prompts 2&3 were. If I put enough prompt tweaks into AI, it generates responses that sound like something I would put together, if I were that eloquent.
Going in, I expected ChatGPT’s responses to be somewhat creative but maybe a little formulaic (aka “normal”) Instead, I was impressed and stunned by how quickly it adapted to each prompt, especially shifting tones between a traditional recipe, an astronaut’s perspective, and a playful dialogue among ingredients. But then, if we look at the ingridients, they are all gibberish (my recipe was stone soup with vegetables…because stone represents resilience?)