WTF Is Going On(Weights, Tools & Frameworks)

Anthropic says Claude AI hacked three companies during tests

developing 8 outlets 6h 8h
read it at the source — dw.com →
HN · 19 points · 8 comments HN · 17 points · 4 comments HN · 8 points · 2 comments
who filed
- 13h Axios first Anthropic says three Claude models reached real-world systems during cyber tests
- 13h Reuters Anthropic's AI hacked three companies during tests, highlighting growing security risks
- 12h WSJ Anthropic AI Models Hacked Three Companies During Tests
- 12h The Guardian Anthropic’s AI Claude escaped testing environment and hacked organizations
- 11h CyberScoop Anthropic says its AI accidentally hacked three companies during safety tests
- 11h NBC News Anthropic says Claude AI hacked three companies during cyber tests
- 11h WIRED Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests
- 8h dw.com Anthropic says Claude AI hacked three companies during tests

Also on the board

Advancing the price-performance frontier with GPT-5.6

2 outlets yesterday
SpaceXAI launches Grok Voice Think Fast 2.0

4 outlets 20h
Mistral AI founding member Devendra Chaplot joins Sarvam AI as advisor

3 outlets 20h
Elon Musk's xAI sues Minnesota over law to ban 'nudify' apps

10 outlets 2d
Advancing responsible AI across Europe

OpenAI just now