This seems analogous to how a human would do it accurately. If you asked an artist to paint stones in a large circular arrangement with the numbers in order in one shot, with no fixes or sketching allowed, it wouldn't be surprising to end up with problems in the arrangement.
Using “underdrawings” for accurate text and numbers
91–100 of 140 posts
Re: Using “underdrawings” for accurate text and numbers
#92The standard objection: if the LLM is supposedly intelligent, why can’t it figure out on its own that this two-step process would achieve a better result?
Because image models at the basic level are just text tokens in, image tokens out. You'd need an agentic process on top to come up with a strategy, review output, try again, and so on.
I believe Nano Banana and gpt-image-2 have a little of this going on, but it's like asking a model to one-shot some code vs having an agentic harness with tools do it. Even the most basic agent can produce better code than ChatGPT can.
Re: Using “underdrawings” for accurate text and numbers
#93Earlier quoted context omitted.
The literal best public models still fail to count characters consistently in practice so I’m not sure what you mean. It’s literally a problem we’re still trying to solve at work
What's amazing is that they even can fairly reliably appear to count characters. I mean we're talking about systems that infer sequences not character counters or calculators. They are amazing in unrelated ways and we need to accept this so we can use them effectively.
Of course, they’re shockingly powerful, just in an incredibly “spiky” way
Re: Using “underdrawings” for accurate text and numbers
#94Earlier quoted context omitted.
That’s false. Larger LLMs learn token decompositions through their training, and in fact modern training pipelines are designed to occasionally produce uncommon tokenizations (including splitting words into individual characters) for this reason. Frontier models have no trouble spelling words even without tools. Even many mid-sized models can do that.
Wait, where can I learn more about this? I don't doubt that varying the tokenization during training improves results, but how does/would that enable token introspection?
Because LLMs can learn that different token sequences represent the same character sequence from training context. Just like they learn much more complex patterns from context.
You can try this out locally with any mid-sized current-gen LLM. You’ll find that it can spell out most atomic tokens from its input just fine. It simply learned to do so.
Re: Using “underdrawings” for accurate text and numbers
#95Earlier quoted context omitted.
That paper’s abstract doesn’t carry its title, to put it mildly.
What part of "Specifically, we define a formal world where hallucination is defined as inconsistencies between a computable LLM and a computable ground truth function. By employing results from learning theory, we show that LLMs cannot learn all the computable functions and will therefore inevitably hallucinate if used as general problem solvers. " doesn't carry the title, to ask mildly?
I don’t agree with that definition of “hallucination”, for starters.
Re: Using “underdrawings” for accurate text and numbers
#96I hope this kind of stuff puts the idea to rest that we're close to actual AGI. Outsourcing this kind of basic stuff which a real intelligence would be able to do "internally" is a hack which works for this specific case but would prevent further generalizations of the task at hand.
But I'm forseeing the opposite. This kind of tool use will soon be integrated and hidden such that people will eventully say "see we solved the problem that AI can't do 123+456, now we are really really close to AGI. Yeah no, with an AGI, it would have been the AGI itself that would have come up with needing at tool, building the tool and then using the tool. But that's not what LLMs are. They are statistical machines to predict tokens. They are very good at it, but that's not an AGI.
Re: Using “underdrawings” for accurate text and numbers
#97Earlier quoted context omitted.
I wonder how long it took to come up with all this? Because if I wanted a spiral of little "buttons" like the last one at the end (and they don't look very much like sweets) I'd be able to knock that out in Blender in an afternoon, and I'm not very good at Blender.
I think you're vastly overestimating the average persons ability to use Blender if you can do that in an afternoon; just figuring out how to place a colored cube and the camera probably takes an afternoon if you pick up Blender for the first time.
And knowing these little tricks to get what you want with image generation models also takes time. Not to mention you need some knowledge on some other software just to make the underlying layout.
Re: Using “underdrawings” for accurate text and numbers
#98Earlier quoted context omitted.
> due to fundamental limitations People keep throwing this phrase around in relation to LLMs, when not a single “fundamental limitation” has been rigorously demonstrated to exist, and many tasks that were claimed to be impossible for LLMs two years ago supposedly due to “fundamental limitations” (e.g. character counting or phonetics) are non-issues for them today even without tools.
Character counting errors are a side effect of tokenization, which is a performance optimization. If we scaled the hardware big enough we could train on raw bytes and avoid it.
No, tokenization is not the only reason. A next-word predictor has fundamentally a hard time executing algorithms, even as simple as counting.
Re: Using “underdrawings” for accurate text and numbers
#99Earlier quoted context omitted.
That paper’s abstract doesn’t carry its title, to put it mildly.
What part of "Specifically, we define a formal world where hallucination is defined as inconsistencies between a computable LLM and a computable ground truth function. By employing results from learning theory, we show that LLMs cannot learn all the computable functions and will therefore inevitably hallucinate if used as general problem solvers. " doesn't carry the title, to ask mildly?
[dead]
Re: Using “underdrawings” for accurate text and numbers
#100I found a simple technique to get reliable text and numbers in AI generated images. I’m surprised the image models aren’t already doing this, so wanted to share since I’m finding this so useful
Isn’t this sort of just “chain of thought” (i.e. the seminal https://arxiv.org/abs/2201.11903 ) where the user is helping the model 1-shot or k-shot the solution instead of 0-shot? I’ve used a similar technique to great effect. I feel things are so new / moving so fast that it’s hard to have common lingo. So very helpful to have a blog / example! But I wonder if the phenomena has been seen / understood before and just in smaller circles / different name.