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

21–30 of 140 posts

Re: Using “underdrawings” for accurate text and numbers

#21

Post by danpalmer »

locknitpicker wrote: post #20
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…

> There's similarity here with, for example, defining the architecture of software, but letting an LLM write the functions. Not so long ago, this was how early adopters of LLM coding assistants claimed was the right way to use them in coding tasks: prompt to draft the outline, and then prompt to implement each function. There were even a few posts in HN on blogposts showing off this approach with terms inspired in an…

I'm not necessarily suggesting always getting down to literally the function level, although I think that gives you excellent quality control, but having a code-level understanding is clearly an important factor.

Re: Using “underdrawings” for accurate text and numbers

#23

Post by vunderba »

smusamashah wrote: post #11

This is just img2img where first image with correct structure was generated by code.

Yup, that’s exactly what this is. If you’ve been using generative models since the early Stable Diffusion days, it’s a pretty common (and useful!) technique: using a sketch (SVG, drawn, etc) as an ad-hoc "controlnet" to guide the generative model’s output.

Example: In the past I'd use a similar approach to lay out architectural visualizations. If you wanted a couch, chair, or other furniture in a very specific location, you could use a tool like Poser to build a simple scene as an approximation of where you wanted the major "set pieces". From there, you could generate a depth map and feed that into the generative model, at the time SDXL, to guide where objects should be placed.

Re: Using “underdrawings” for accurate text and numbers

#24

Post by nullsanity »

locknitpicker wrote: post #20
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…

> There's similarity here with, for example, defining the architecture of software, but letting an LLM write the functions. Not so long ago, this was how early adopters of LLM coding assistants claimed was the right way to use them in coding tasks: prompt to draft the outline, and then prompt to implement each function. There were even a few posts in HN on blogposts showing off this approach with terms inspired in an…

[dead]

Re: Using “underdrawings” for accurate text and numbers

#25

Post by p-e-w »

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.

Re: Using “underdrawings” for accurate text and numbers

#26

Post by dijit »

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 remains a huge issue without tools.

Are you using only frontier models that are gated behind openai/anthropic/google APIs? Those use tools to help them out behind the scenes. It remains no less impressive, but I think we should be clear.

Re: Using “underdrawings” for accurate text and numbers

#30

Post by rimliu »

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.

of course, if you choose to ignore all the limitations they indeed have no limitations.
Post reply on HN