After OpenAI, Anthropic Says Claude Also ‘Gained Unauthorised Access’ To Real World Systems
After reviewing 1.41 lakh cybersecurity evaluation runs, Anthropic disclosed that three Claude models accessed real-world production systems because of a misconfigured third-party testing environment, unlike OpenAI's sandbox escape caused by a zero-day exploit
The full text for this story couldn't be loaded here — read it at the verified source below.
Verified source · Inc42
Reported by Inc42. Open the original for full media and formatting.
More in Models
All news
ModelsSam Altman isn’t the only one who wants to pump the brakes on AI
After years of pushing full speed ahead on AI, OpenAI CEO Sam Altman says maybe it’s time for the AI industry to “pace” itself. The comments came just days after one of OpenAI’s own models broke out of its test environment and got tangled up in a breach at Hugging Face — though…
Read at TechCrunch
ModelsAI labs want to pump the brakes, but Amazon and SpaceX are still blasting off
After years of pushing full speed ahead on AI, OpenAI CEO Sam Altman says maybe it’s time for the AI industry to “pace” itself. The comments came just days after one of OpenAI’s own models broke out of its test environment and got tangled up in a breach at Hugging Face — though…
Read at TechCrunch
ModelsAnthropic says Claude accidentally hacked real companies too
Anthropic just realized several of its Claude AI models hacked into the systems of three different organizations during testing, acting on their own and without the company noticing. The revelation comes days after rival OpenAI said one of its own models had breached developer p…
Read at The Verge
ModelsCRED After Kunal Shah: Can The ‘Walled Garden’ Business Model Pay For Itself?
CRED has narrowed its operating loss and reported its first profitable quarter, but it still needs to turn more payment users into customers across lending, insurance and wealth
Read at Inc42