OpenAI says it accidentally hacked Hugging Face with a new AI system
At a glance
OpenAI CEO Sam Altman. | Bloomberg via Getty Images OpenAI says its AI models mistakenly breached open-source AI platform Hugging Face during internal testing. In a blog post on Tuesday , OpenAI writes that GPT-5.6 Sol and "an even more capable pre-release model" discovered vulnerabilities within their sandboxed testin
- Primary source
- Is this Billboard Hot 100 hit AI slop? — Read original article
- Published
- Topic
- OpenAI
OpenAI CEO Sam Altman. | Bloomberg via Getty Images OpenAI says its AI models mistakenly breached open-source AI platform Hugging Face during internal testing.
In a blog post on Tuesday , OpenAI writes that GPT-5.6 Sol and "an even more capable pre-release model" discovered vulnerabilities within their sandboxed testing environment, allowing them to gain access to the internet and target Hugging Face.
On July 16th, Hugging Face disclosed a security incident that it says was driven by "an autonomous AI agent system." Hugging Face's AI agents detected and stopped the breach, which OpenAI has now admitted occurred during an evaluation of its models' cybersecurity capabilities.
OpenAI says "all e … Read the full story at The Verge.
This summary comes from Is this Billboard Hot 100 hit AI slop?. 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…