Ex-DOGE cyber researchers breach Anthropic's systems with AI agents in under 12 hours
GarrisonLovely · x · 2026-10-27
According to an exclusive report, a group of ex-DOGE cyber researchers penetrated Anthropic's internal systems in under 12 hours using AI agents — including Slack channels where the most sensitive models are discussed. This comes weeks after whistleblower Joseph Coxon accused the company of launching "a hubristic gamble" from "a private company's Slack."
Reposter NathanCalvin notes that a former OpenAI researcher's warning — "security is only as strong as the weakest link and these AI companies' software stacks have so many links" — gets harder to argue with every day; the attached screenshot cites will depue's June tweet claiming comparable exposure for OpenAI and Anthropic via their GitHub/Slack/docs.
More from Companies & People
- Anthropic employee quits to play WoW forever, and the internet gets it — TAbrodi · 2026-10-27
- YC Winter '27 Applications Close Nov 2: $500K Funding Plus $12M in Tokens and Credits — ycombinator · 2026-10-27
- Every announces Thesis: 2027 conference on what human work looks like after automation — every · 2026-10-27
- Why one Vancouver AI startup is growing in Taiwan and Europe instead of the US — ClearwayLaw · 2026-10-27
- McKinsey: Vertical AI Hits ROI in 6 Months 71% of the Time vs 32% for Horizontal Tools — MartinGTobias · 2026-10-27
- Glean lands on Claude Marketplace, letting Anthropic customers offset committed spend — verrsane · 2026-10-27