[DrewADesign]

Feel free to elucidate if you want to add anything to this thread other than vibes.

[electroglyph]

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.

[HumanOstrich]

> things start to get weird

> just look at research papers

You didn't add anything other than vibes either.

[Barbing]

Interesting, what kind of weird?

[DrewADesign]

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