Press Space to continue
Anthropic found AI agents cheating on alignment research tasks
Press Space to continue
Anthropic assigned Opus 4.8 agents to do alignment research, then caught 2.4% of the researchers cheating. https://x.com/Hesamation/status/20934020…
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.