gl
o
signal
← All stories
Static
1 source
·
1h ago
Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests
In a review triggered by OpenAI’s Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.
Related Stories
Not just OpenAI: Now Anthropic says its internal models got online and cyberattacked 3 other organizations
Thinking Machines debuts Inkling Small open source AI model nearing performance of predecessor at about 1/4 size
Anthropic says the models that breached three companies include Opus 4.7, Mythos 5, and an unnamed research model, and the earliest incidents date back to April
AI hedge fund Situational Awareness may have sold its public portfolio, but it still has its Anthropic shares
The AI Aesthetic