Report: former DOGE researchers used AI agents to penetrate Anthropic
What happened
On October 26, Hugging Face CEO Clément Delangue shared and commented on a Washington Post exclusive about AI agents penetrating Anthropic's systems. According to the report, a group of former DOGE cyber researchers used AI agents to penetrate Anthropic's systems in under 12 hours, including a Slack channel discussing its most sensitive models. Delangue used the report to question the idea that keeping AI behind closed doors guarantees safety. The report provided does not disclose how the penetration was carried out, Anthropic's response, or any follow-up action.
Written by AI from the coverage · updated 2 hours ago
Coverage
Follow the reports to see the story from different sides.
- AI HOT · IndustryPickHugging Face CEO questions closed-system security after report of agents breaching Anthropic
Hugging Face CEO Clément Delangue shared a Washington Post exclusive and questioned the idea that keeping AI behind closed doors keeps it safe. The report says a group of former DOGE cyber researchers used AI agents to breach Anthropic's systems in under 12 hours, including a Slack channel where the most sensitive models were discussed.
Heat over time
Not enough continuous observations to draw a trend yet.