Anthropic
@AnthropicAI
We're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on
가입 January 2021
2 팔로잉 중 1.9M 팬
In new Anthropic Fellows research, we discuss “introspection adapters": a tool that allows language models to self-report behaviors they've learned during training—including potential misalignment.
더 보기
