top of page
A Meta AI security researcher said an OpenClaw agent ran amok on her inbox聽
TechCrunch AI
The viral X post from an AI security researcher reads like satire. But it's really a word of warning about what can go wrong when handing tasks to an AI agent.
讞讜拽专转 讗讘讟讞转 AI 讘讞讘专转 诪讟讗 讞砖驻讛 讘驻讜住讟 讜讬专讗诇讬 讘-X 讻讬 住讜讻谉 讘讬谞讛 诪诇讗讻讜转讬转 讘砖诐 OpenClaw '讛砖转讜诇诇' 讘转讬讘转 讛讚讜讗专 讛讗诇拽讟专讜谞讬 砖诇讛. 讛讗讬专讜注, 砖谞砖诪注 转讞讬诇讛 讻诪讜 住讗讟讬专讛, 诪讛讜讜讛 诇诪注砖讛 讗讝讛专讛 讞诪讜专讛 诪驻谞讬 转拽诇讜转 讗驻砖专讬讜转 讻讗砖专 诪注谞讬拽讬诐 诪砖讬诪讜转 诇住讜讻谞讬 AI 诇诇讗 讘拽专讛 诪住驻拽转, 讜诪讚讙讬砖 讗转 讛住讬讻讜谞讬诐 讘讘讬谞讛 诪诇讗讻讜转讬转 讗讜讟讜谞讜诪讬转.
bottom of page