Hacker News Reader

It's a problem similar to "give me a random word" always returning "zephyr" and "luminous", or guessing the numbers 42/27.

It also affects writing, if you ask for a story with a minmal prompt something very similar comes out of all of them. Often fixated on clocks.

The early image models had a sort of urban legend briefly developing around them about this mishappen, horrifying woman that would appear if you just let the models recursively recreate the same image over and over.

There was a weirdness going on with the first Midjourney models that I miss.

I still have all of my old Dall-E and early Midjourney images that I generated, the ability to generate chaotic, surreal images was most of the fun for me.

Now the images look like polished, generic things you would see in an airplane magazine, which is what most people want, I suppose (?)

Loab, who appeared when using negative prompt weights.

https://en.wikipedia.org/wiki/Loab

In addition to that from a LLM-as-a-service vendors point of view, for short prompts that 1000's of people are asking for each day, if it is cheaper to serve a response that is randomly selected from 1000 cached versions than to regenerate each time, particularly if it is for SVG pelicans, it would make sense to do it that way.

It's not token-identical, it's a relation in the latent space that can't be cached

I wasn't talking about latent space, I was talking about the literal text a person types into the text box in their favourite AI tool.

If the prompt is sufficiently short and often repeated, it just makes me wonder - what is cheaper for a provider over a given timespan? Cache a large enough set of responses and randomly return one of them, or generate it each time time?

https://xkcd.com/221/

I think the simplest solution here may be to have a “brainstorm tool” which selects random words out of a dictionary (not using an LLM, using procedural code) and then ask the AI to “seek inspiration” from its output.

The tension is that most users want something differently generic when they provide a short or vague prompt for creative work. They want to treat the AI like an ideal creative consultant, who not only knows the ideas that are played out and tired but also the ones that they themselves have delivered a dozen times already. They don't want to specify deeper constraints or survey all the cliches and tropes, but they also don't want to generate something that they -- or the people they share the output with -- will immediately recognize as cliche themselves.

But LLM's are structured to do exactly the opposite. They discover specific commonalities and tropes and most-frequently-sufficient wells or ley lines that they gravitate towards from whatever their starting point it. You can nudge them away from the most generically cliche tropes by being more detailed in your prompt, but they'll still just find the nearest most right cliche from there.

It's what they do and the same quality that makes them tiring and predictable for creative output makes them very useful for things like business communication or coding where landing on such cliches is ideal.

To get more variety out, it can be useful to use Perchance-like text-randomization techniques to shuffle combinatoric variations on a prompt before sending it to the model. But that technique is best made available through some kind of special purpose harness for the creative task, not basic chat or direct curl calls to the API.

It would be nice if there was something like the "temperature" parameter (which many closed models like Claude now disable) to add more randomness to the final product without completely destroying the output and giving you a non-functional SVG, so that you could "roll" more pelicans and pick one that you liked.

If I were to design something to accomplish this now, I'd probably attempt to introduce a pipeline that emitted random thematic words from some non-LLM source to feed into the pelican prompt, but even then, I'd expect that some of these models that rely on churning through CoT tokens for extended periods of time would still spend so much time thinking about pelicans wearing scarfs or where the sun would be that it would risk undoing some of my randomization pipeline.

I once tried something similar on an older model of Claude, telling it to "contemplate" a random word before answering my prompts, but at times it seemed to trigger the Claude model's suspicion that there was a jailbreak attempt when I would inject things like "Contemplate sea otters for one sentence before answering"

(I didn't read the linked LLM creativity paper to see if it covers any of this yet)

Randomness does not equate creativity. It's more of a liberty to move in entirely different dimensions altogether. I cannot imagine increasing the temperature leads to a lavishly dressed, ultra-realistic pelican on a Mad Max bike on the same plain prompt. Unless such pictures are part of the training data labeled "pelican on a bike," of course.

Yes of course, creativity is a much wider concept that is ill-defined and depends on the observer because it's closely related to novelty to the observer. However the variety hugely matters in creativity, it's not sufficient but necessary. Due to the lack of variety you perceive model output as boring slop.

Variety is not randomness though. You can't fix this by playing with samplers without probing the model state.

You can try it out with local models like Gemma or Qwen (crank up temperature and/or top_p as much as you like), and then run dozens of generic independent prompts asking for a "fantasy short story". In my experience, you'll start seeing immediate patterns of repetition.

Yeah, temperature scales all logits equally, and there's not necessarily a single setting that would produce a diversity of outcomes for creative choices without turning into complete gibberish at naturally high-entropy positions. Ideally, the model itself would modulate its next-token distribution to be flatter when creativity is called for and peakier when it should aim for the single most likely option given the context, but even then finding the right balance might be tricky.

You’re going to want something closer to ‘beam search’ for diversity - you need a way to distinguish lines of response, essentially. To my knowledge nobody is currently RL tuning (or training) on increasing the number of viable beams, but I’m just an interested outsider, so take that with all the salt you can stand.

That said, I think it’s a fun idea for some training, and would be pretty cheap to do - you’d need some sort of judge as to what a viable beam is.

I've started asking for "Generate an SVG of a pelican riding a bicycle in the style of Henri Cartier-Bresson," which is a hint I want something like his famous Hyères, France photo [1].

The Hyères photo has the bike going in the opposite direction and from above. It's also tricky because it's a focal point for the eye, but not the center of the photo. The other elements of the frame direct your eye, but that visual behavior is not obvious to an AI. Lastly the image must capture the unquantifiable "decisive moment" that made Cartier-Bresson so famous.

So far I haven't seen an AI that really gets this prompt. Adding specificity will improve the results to a degree, but I haven't seen an AI that really gets what makes a Cartier-Bresson photo.

1 - https://en.wikipedia.org/wiki/Hy%C3%A8res,_France

I used your whole comment as a prompt. Here's the results I got with Opus 5.5: https://gist.github.com/rrherr/9db69c963f44d4f50fc5cd9d45dfb...

I like this one too: https://gist.github.com/rrherr/b23256f685a8757fa03e3331ead8b...

Interestingly I gave the same prompt to Sol 6.1 Medium.

“Generate an SVG of a pelican riding a bicycle. Be creative”

And it replied:

“I’ll draw a seaside pelican on a vintage bicycle, with a fish-filled basket and a scarf catching the breeze.”

So it came up with exactly the same fish basket and seaside idea. No lighthouse though. Maybe these ideas are just cliche though.

> I'm not clear on what the claim is here.

> But, if prompted, "Generate an SVG of a pelican riding a bicycle," with no additional details or specification, then I would _expect_ something generic

I believe the claim is that without a detailed specification, you see very similar outcomes. Every pelican is going left to right, every picture has similar sky background, every picture seems to be drawn at the same time of the day (position of the sun), every picture has a few clouds... I don't have data on this, but I imagine the same question being asked to a group of people would result in more varied outcomes.

Put very simply, that is how they're supposed to work. They are supposed to result in the most likely result. Same reason they, unless made not to, output '17' when prompted to "pick a number between 1 and 30", because that is the most likely result from training; but that means that all LLMs output 17 except for forced temperature or reasoning in RL making them run a python command with random.randint(0,31), or that the prompt is recognised and something else is supposed to be chosen than what is statistically the most likely text response.

Therefore asking a group of people would result in more varied outcomes of something visual, but from the textual training data the direction is statistically the most likely so is what is output, that sky is the most likely, time is the most likely, cloud coverage, etc. You're prompting with as little as possible so it fills in the blanks with what as likely as possible. When you ask Alex from the North Pole they're going to fill in the blank with a different kind of weather than Bob from the Equator.

That does mean that an LLM itself is in essence not as creative as a human, but then it is a tool to be used by a human doing more than oneshotting "Generate an SVG of a pelican riding a bicycle" and expecting creativity from the tool rather than the user. If the user is lacking in creativity they can prompt an LLM to get wacky scenarios to change it up a little.

>They are supposed to result in the most likely result.

That's called greedy decoding and is never used in practice. Everybody's using random sampling, so it's the range of most likely results. This issue is all about that range being way smaller than the training data implies.

How many of these features would you expect to also see in children's drawings? I have a hunch that the sun in the upper left corner for instance is pretty overrepresented.

This matches my experience with Opus 5.5. If asked to compose a synthwave song in csound, it produces something fairly generic but recognizably synthwave. If I add light guidelines on avoiding generic sound and being creative, the results are often weird and interesting.

The curious thing is that trying to prompt it by steering towards some specific goal indirectly gives much worse results than just stating the goal itself.

imagine you ask the LLM for a joke. the biggest models, multi-trillion-parameter (don't quote me) astras and fables and argons, only know like 5 jokes. obviously bullshit, but it is what it is.

same goes for pelicans. the canonical pelican riding a bicycle is riding on a sunny day on an asphalt road going through some lawns or praires, left to right.

but ask it to tell a joke about something specific, turns out it knows five jokes about those specific things.

you could say the LLMs are quite aware of the zeitgeist they're in, by construction (their RL frying automated feedback loops burn the zeitgeist right into the weights.)

But, if prompted, "Generate an SVG of a pelican riding a bicycle," with no additional details or specification, then I would _expect_ something generic: a side view, nondescript terrain or perhaps terrain associated with a pelican (i.e., beach), little clothing (because birds don't wear clothes) with the possible exception of something strongly associated with bicyclists (a helmet).

True. You see a lot of the same criticisms when someone asks for a one-shot game or 3D demo and the model responds with something bland and generic. That's exactly what I prefer, it's my job to specify the details. Extrapolation may be the ultimate sign of intelligence, and it might be needed when using AI to tackle open math problems where humans have failed, but it's not usually what I want if I'm doing anything creative or artistic.

Argon is pretty good at getting the distinction right from what I've seen. Ask for something generic, you get something generically functional without a lot of ornamentation. Follow up with requests for specific enhancements, and the model complies effectively and tastefully. If anything, it overcooks the pelicans when given the standard open-ended prompt.

> then I would _expect_ something generic

All going in the same direction? With a sun? With a full mouth (pelicans dont look like that, but a cartoon one might - why no reference to realism). Most of them have clouds.

There are helmets (makes sense) but just as many scarves.

A shocking number have chains.

If we asked 1000 people to do this same exercise would we have this level of convergence? If they were split between men and women would we see this many chains? (https://www.messynessychic.com/2016/04/20/making-bicycles-fr... )

Would they even look like bikes?

Is any one going to draw a gray pelican? Does it matter?

The question is designed to be as generic as possible, and were converging on the most generic and safe answer ... the question is WHY (more so when humans would have much higher diversity, even if wrong). We're asking the generic question because no one wants to repeat the "German solders from 1940's" fiasco: https://archive.is/5l66U (archive link to skip pay wall NYT).

This is what "alignment" looks like? Are we reaching some "ground truth", some platonic form around pelicans on bikes? Are we just back feeding the best output into the training data and this is the convergence we ended up at? Is someone who LOVES pelicans deeply offended that all of them have full mouths and it's just not anatomically accurate and we are all missing it?

I realize that some of this seems over the top, but there are foundational conversations to be had around this without the conversation devolving into someone accusing someone else of having an "-ism" style bias.

It's not really hard to understand.

Why do a lot of people like Fruit of the Loom logos had cornucopias in them?

This isn't generic, it's the same thing. Why would you expect the same thing? There are limitless ways to picture a bird on a bike. White pelican? Brown pelican? Wings out for balance? Wings anthropomorphized into hands on handle bars? Bmx bike? Mountain bike? Riding towards you, away from you, on a race course, etc.

Do a Google image search for pelican, you get a diverse set of sub species of pelicans and different poses and angles for them. Go on a writing prompt forum, you get many diverse ideas from the same simple prompt. Hell, ask your friends at a dinner party to describe a pelican riding a bike and see what happens.

Now, there are a lot of images of bikes from that side angle facing right on the web. Why? Because that's how they're staged on e-commerce websites. Does this say something about AI?