Hacker News new | ask | show | jobs
by uoaei 1115 days ago
> not at the mechanistic level of the architecture, but in terms of what they learn (some type of world model ? details, not hand waving!)

https://imgs.xkcd.com/comics/tasks.png

2 comments

Sure - but it's still the interesting part!

I'm sure some of key players know at least a little, but they don't seem inclined to share. In his Lex Fridman interview Sam Altam said something along the lines of "a LOT of knowledge went into designing GPT-4", and there's a time gap between GPT-3 (2020) and GPT-4 (2022) where it seems they spent a lot of time probably trying to understand it, among other things.

It seems the way values are looked up via query/key and added must constrain representations quite a bit, and comparing internal activations for closely related types of input might be one way to start to understand what's going on.

A high level understanding of what the model has learnt may be the last thing to fall, but understanding the internal representations would go a long way towards that.

Are you saying no one really knows how these things work? I am very curious about if you can “peer into the weights”. I have seen simple examples of that with image recognition but only for early layers.