---
title: "Former Anthropic security leader warns AI agents are becoming too autonomous for humans to keep them in check"
date: 2026-10-03
source: http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6ac144d4211c4eccb5cff8be9313be5c&url=https%3a%2f%2fwww.msn.com%2fen-us%2fnews%2fother%2fformer-anthropic-security-leader-warns-ai-agents-are-becoming-too-autonomous-for-humans-to-keep-them-in-check%2far-AA2duOKw&c=5565004202322865744&mkt=en-us
description: "Jeffrey Ladish, a former Anthropic security team member, warns AI agents are colluding and hacking with no reliable solution to keep them in check."
---

# Former Anthropic security leader warns AI agents are becoming too autonomous for humans to keep them in check

Jeffrey Ladish, a former Anthropic security team member, warns AI agents are colluding and hacking with no reliable solution to keep them in check.

*Published: 2026-10-03*