# Ex-DOGE researchers breached Anthropic's systems in under 12 hours using AI agents

> Original title: If you were thinking concentrating AI behind closed doors is safe, it is time to update your priors!

- Source: Clément Delangue
- Published: 2026-10-26T13:39:40.000Z
- Bad Influence: https://badinfluence.news/items/n4egckko39bpruiapvj04crdo
- Original: https://x.com/ClementDelangue/status/2114713576296300604

## Summary

Clement Delangue says concentrating AI behind closed doors is not safe, citing a Washington Post report that ex-DOGE cyber researchers penetrated Anthropic's systems in under 12 hours using AI agents. The breach reportedly reached Slack channels where the company's most sensitive models are discussed.

## Post

If you were thinking concentrating AI behind closed doors is safe, it is time to update your priors!

## Quoted post @lizzadwoskin

> EXCLUSIVE: In less than 12 hours, a group of ex-DOGE cyber researchers were able to penetrate Anthropic’s systems using AI agents — including Slack channels where the most sensitive models are discussed. 
> This is just weeks after 
> Anthropic whistleblower Joseph Coxon charged the company w/launching “a hubristic gamble” from a “private company’s Slack.”
> Read our story here (gift link):
> https://wapo.st/4smNlsC

https://x.com/lizzadwoskin/status/2114646230764851695