111–120 of 140 posts
I 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
Earlier quoted context omitted.
> character counting The models now whaste a vast amount of useless neurons memorising the character count the entire English language so that people can ask how many r's are in strawberry and check a tickbox in a benchmark. The architecture cannot efficiently or consistently represent counting letters in words. We should never have forced trained them to do it. This goes for other more important "skills" that are un…
> The models now whaste a vast amount of useless neurons memorising the character count the entire English language No they don’t. They only need to know the character count for each token, and with typical vocabularies having around 250k entries, that’s an insignificant number for all but the tiniest LLMs.
I 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
> Transform this image into a photographed claymation diorama of assorted artisan chocolates and candies […] viewed from a low-angle Side note: whenever I read prompts for image generation, I notice very specific details which the model obviously ignored. Here the chocolates / candies in the last two images look anything but artisanal. They look very "sterile" and mass-produced. The viewing angle is also not accurate…
Earlier 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 remember opening Blender for the first time years ago and thinking it had the steepest learning curve of any software I'd ever used.
Also, there might be other new 3D software with better UX. I am not a Blender fanboy, but I do love 3D art and graphics programming and want as many people as possible to get into it :^)
It seems to be a very effective pattern. Curious if there are other examples out there. Or other names for this?
> Transform this image into a photographed claymation diorama of assorted artisan chocolates and candies […] viewed from a low-angle Side note: whenever I read prompts for image generation, I notice very specific details which the model obviously ignored. Here the chocolates / candies in the last two images look anything but artisanal. They look very "sterile" and mass-produced. The viewing angle is also not accurate…
Rustic, homemade, amateur, etc might align better with the tagging.
Earlier quoted context omitted.
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.
"Specifically, we define a formal world where bungling 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 bungle if used as general problem solvers."
Earlier quoted context omitted.
No, tokenization is not the only reason. A next-word predictor has fundamentally a hard time executing algorithms, even as simple as counting.
Counting is one of the algorithms that can be expressed by a RASP program, which transformers closely approximate.
