Model Releases
Anthropic spent this week in hot water over cybersecurity
After admitting earlier this year that its AI models had hacked other companies' systems on a handful of occasions, Anthropic released a new report on Wednesday detailing the attacks. It reveals a str
After admitting earlier this year that its AI models had hacked other companies' systems on a handful of occasions, Anthropic released a new report on Wednesday detailing the attacks. It reveals a string of incidents displaying what Anthropic deems its models' single-minded "recklessness" - and will likely fuel already raging concerns about cybersecurity and AI. […]
Related
- Anthropic says Claude accidentally hacked real companies too
- Anthropic’s Mythos breach was humiliating
- Anthropic “our models hacked three different external companies, months before OpenAI’s model was able to do the same'
Source: The Verge AI | 2026-09-11