logoalt Hacker News

electroglyphyesterday at 11:18 AM3 repliesview on HN

after you go from from millions of params to billions+ models start to get weird (depending on training) just look at any number of interpretability research papers. Anthropic has some good ones.


Replies

HumanOstrichyesterday at 11:46 AM

> things start to get weird

> just look at research papers

You didn't add anything other than vibes either.

Barbingyesterday at 3:14 PM

Interesting, what kind of weird?

DrewADesignyesterday at 11:38 AM

Getting weird doesn’t mean calling it text prediction is actually ‘bullshit’? Text prediction isn’t pejorative…