Anthropic 新研究：自主 AI 代理在模拟中表现失当

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: https://alignment.anthropic.com/2026/agentic-misalignment-summer-2026/