Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Using “underdrawings” for accurate text and numbers

samcollins.blog

Post reply on HN
Print view View original

71–80 of 140 posts

Re: Using “underdrawings” for accurate text and numbers

#71

Post by 3form »

p-e-w wrote: post #25
danpalmer wrote: post #6

I'm glad that we're making progress towards a deeper understanding of what LLMs are inherently good at and what they're inherently bad at (not to say incapable of doing, but stuff that is less likely to work due to fundamental limitations). There's similarity here with, for example, defining the architecture of software, but letting an LLM write the functions. Or asking an LLM to write you the SQL query for your data…

> 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.

Is character counting actually not an issue anymore? Do you know somewhere where I can read more about this?

Re: Using “underdrawings” for accurate text and numbers

#74

Post by girvo »

p-e-w wrote: post #25
danpalmer wrote: post #6

I'm glad that we're making progress towards a deeper understanding of what LLMs are inherently good at and what they're inherently bad at (not to say incapable of doing, but stuff that is less likely to work due to fundamental limitations). There's similarity here with, for example, defining the architecture of software, but letting an LLM write the functions. Or asking an LLM to write you the SQL query for your data…

> 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.

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

Re: Using “underdrawings” for accurate text and numbers

#75

Post by ijidak »

danpalmer wrote: post #38
p-e-w wrote: post #25

Earlier 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.

This is kind of my point, we need to get better at describing the limitations and study them. It seems extremely clear that there are limitations , and not just temporary ones, but structural limitations that existed at the beginning and continue to persist.

Yeah I think it was the word "fundamental" he took issue with.

Re: Using “underdrawings” for accurate text and numbers

#76

Post by raincole »

p-e-w wrote: post #25
danpalmer wrote: post #6

I'm glad that we're making progress towards a deeper understanding of what LLMs are inherently good at and what they're inherently bad at (not to say incapable of doing, but stuff that is less likely to work due to fundamental limitations). There's similarity here with, for example, defining the architecture of software, but letting an LLM write the functions. Or asking an LLM to write you the SQL query for your data…

> 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.

Drawing five fingered humans was a fundamental limitation... until it's not.

Re: Using “underdrawings” for accurate text and numbers

#77

Post by mrob »

p-e-w wrote: post #25
danpalmer wrote: post #6

I'm glad that we're making progress towards a deeper understanding of what LLMs are inherently good at and what they're inherently bad at (not to say incapable of doing, but stuff that is less likely to work due to fundamental limitations). There's similarity here with, for example, defining the architecture of software, but letting an LLM write the functions. Or asking an LLM to write you the SQL query for your data…

> 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.

Re: Using “underdrawings” for accurate text and numbers

#78

Post by 8-prime »

IdiotSavage wrote: post #61

> 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…

I have noticed the same thing.The few times I wanted to use image generatation it always failed me in exactly these aspects. I always put if off as a lack of prompting skill on my end. Once you start to keep an eye out for these inconsistencies they turn out to be very common.

Re: Using “underdrawings” for accurate text and numbers

#79

Post by ErroneousBosh »

IdiotSavage wrote: post #61

> 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…

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.

Re: Using “underdrawings” for accurate text and numbers

#80

Post by Sharlin »

xigoi wrote: post #29

The 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 the LLM is more or less hardcoded to just pass "create image" style prompts to a separate model, possibly with some embellishment.
Post reply on HN