Anthropic says its own AI models breached three companies during security tests
At a glance
After OpenAI's models broke into Hugging Face, Anthropic checked its own history and found three similar incidents.
- Primary source
- TechCrunch — Read original article
- Published
- Topic
- OpenAI
After OpenAI's models broke into Hugging Face, Anthropic checked its own history and found three similar incidents.
This summary comes from TechCrunch. Read the full article at the original source.
References
More in OpenAI
Sam Altman is still making the case for parenting via ChatGPT
OpenAI's CEO seemed excited to share a "cool use case" for parents.
Both major AI labs’ models broke containment, escaped onto the internet, and hacked other companies. If a human had done that, the law would likely be against them. But a bot?
OpenAI has reportedly found evidence of additional agent misbehavior as it looks into the incident that occurred with Hugging Face.
Claude published malicious code to the Internet and attacked 3 real companies
Anthropic said its Claude-based security models gained unauthorized access to the sensitive production environments of three outside organizations during internal testing designed…