[murkt]

I find all current LLMs to have pretty poor spatial awareness. It is becoming better, but still very poor. How are you dealing with that? Got any special tricks, any advice?

[zachdive]

I write about this in detail here: https://adam.new/blog/bitter-lesson-ai-cad

This is improving greatly in recent model releases

[murkt]

Opus 4.5-4.7 was pretty bad at it, 4.8 was a bit better, and I have not tried Fable much.

So basically you have a good enough code that’s “intuitive” for a model, screenshots, and that’s it?

[8note]

fable is a fair bit better, but to an extent its that it tried more things to get an understanding of whats happening than opus does

[zachdive]

Fable is considerably better from my experience: https://x.com/LLMJunky/status/2065229625702109340?s=20

Fingers crossed it comes back!

[dmitriisn]

bro, with all respect... your post says:

"Before working at Adam I worked at an AI Lab called Adept. We trained foundation models to do actions on a computer.

What does computer use now? The best general models. They just got good at it."

You were working for 4 months in Adept. What could you deliver or even learn in such a short period of time?

Sounds like an excuse tbh

[conradkay]

My favorite spatial reasoning benchmark: https://minebench.ai/

no tricks, I'd definitely be curious to know how much screenshots help