| ▲ | electroglyph 7 hours ago | |
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 6 hours ago | parent | next [-] | |
> things start to get weird > just look at research papers You didn't add anything other than vibes either. | ||
| ▲ | Barbing 3 hours ago | parent | prev | next [-] | |
Interesting, what kind of weird? | ||
| ▲ | DrewADesign 6 hours ago | parent | prev [-] | |
Getting weird doesn’t mean calling it text prediction is actually ‘bullshit’? Text prediction isn’t pejorative… | ||