Press Space to continue
AAR (Automated Alignment Researcher) methods can now match
Press Space to continue
'AAR methods also outperform ideas from 28 experienced researchers on the same benchmarks, typically within one working day.' Paper: https://www-cdn.anthropic.com/7b1c44894e… https://x.com/AndrewCurran_/status/20933…
Anthropic@AnthropicAIAug 28
New Fellows Research: Can Claude autonomously align other AIs? We gave Claude 48 hours and 1 GPU to improve the alignment of small models. It researched and proposed methods, then trained and tested the models on its own. It worked surprisingly well. https://www.anthropic.com/research/automated-researchers-mitigate-alignment-failures
open on x · 1 viewViews and clicks count once per visitor per day. Clicks are opens of this post on X.