Reading List
Anthropic finds that LLMs trained to "reward hack" by cheating on coding tasks show even more misaligned behavior, including sabotaging AI-safety research (Anthropic) from Techmeme RSS feed.
Anthropic finds that LLMs trained to "reward hack" by cheating on coding tasks show even more misaligned behavior, including sabotaging AI-safety research (Anthropic)
Anthropic:
Anthropic finds that LLMs trained to “reward hack” by cheating on coding tasks show even more misaligned behavior, including sabotaging AI-safety research — In the latest research from Anthropic's alignment team, we show for the first time that realistic AI training processes can accidentally produce misaligned models1.