AI models aren’t yet general-purpose alignment scientists. Progress isn't as easy to verify on most alignment research tasks: our AARs would find “fuzzier” research much harder. But our experiment does show that Claude can increase the rate of experimentation and exploration.

[X] AnthropicAI 관련 핵심 내용을 짧게 정리한 기사입니다. · AI models aren’t yet general-purpose alignment scientists. Progress isn't as easy to verify on most alignment research tasks: our AARs would