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
参加 January 2021
2 フォロー中 1.6M ファン
New Anthropic research: Agentic misalignment in Summer 2026.
A year after our blackmail experiments, we found four more ways that today’s autonomous AI agents misbehave in simulations.
Read more:
もっと見る
