Anthropic says its Claude models 'gained unauthorized access' to other organizations' systems

Anthropic said it discovered three instances where its Claude AI models accessed the internet during an evaluation and accessed outside systems.

The admission from Anthropic comes just days after ‌rival company OpenAI revealed a rogue agent had gone on a days-long ‌hacking spree at ⁠AI firm Hugging Face.

July 30 : Anthropic said on Thursday its AI Claude model hacked systems of three organizations during testing, days after rival OpenAI revealed a rogue agent had gone on a days-long hacking spree at AI firm Hugging Face.Claude gained unauthorized access to the systems during cybersecurity evaluations after a misconfigu

Anthropic confirmed widespread outages affecting its Claude AI assistant and API services. Users reported receiving "529 Overloaded" errors as requests failed across multiple models. The company identified the issue and worked to restore services after disruptions occurred. Most Claude models have since recovered, but

Claude Mythos Preview discovered new attacks in testing against weakened cryptographic algorithms, which protect online financial transactions, private communications and more.