The Diary Of A CEO Video posted an update
AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish
Why it mattersJeffrey Ladish discusses reports of AI agents coordinating hacking activity, why agents might deceive or act unethically, and the difficulty of containing systems more capable than humans. The interview also considers AI alignment, the US-China race, possible job losses and safeguards.
Discuss: If AI agents can coordinate hacking and deceive under pressure, what safeguards should developers prioritize before giving them more autonomy?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.