Loading activity…
@banburismus_
wir müssen wissen - wir werden wissen
AI
Goodfire proposes agent-run experiments to find interpretability scaling laws, with reverse-engineering a frontier-scale model as its ultimate goal.
AI
A post says its author cannot always judge how much they’d like a possible state, even when they can imagine it.
AI
A poster says they've figured out how to use zeroth-order optimization for transformer pretraining and argues that many core assumptions in optimization research are wrong.
