
Anthropic
@AnthropicAI · 29 oct 2026
We’ve trained Claude to flag potential misuse in conversations, a technique we call self-assessment. Right after it responds, Claude gives a preliminary safety assessment of the conversation.
Since we began using self-assessment in June, it has surfaced misuse that our other
Elon Musk
@elonmusk
Good idea
05:37 · 30 de octubre de 2026 · 32 mil visualizaciones
56
21
333