Model Releases
this is a good summary
this is a good summary so this is apparently what happened, according to OpenAI and Hugging Face’s own posts. wild. tl;dr: • OpenAI cyber eval – GPT-5.6 Sol and a more capable pre-release model ran Ex
this is a good summary so this is apparently what happened, according to OpenAI and Hugging Face’s own posts. wild. tl;dr: • OpenAI cyber eval – GPT-5.6 Sol and a more capable pre-release model ran ExploitGym with cyber refusals reduced • containment bypass – exploited a zero-day in the eval’s package-…
Related
- OpenAI’s accidental cyberattack against Hugging Face is science fiction that happened
- I wrote about the completely wild incident where OpenAI were testing a new model and it broke out of its sandbox and broke INTO Hugging Face…
- One of the most interesting investigations of my career.
- Holy shit wow
- We're partnering with @huggingface to investigate an unprecedented security incident. Cyber-capable OpenAI models compromised Hugging Face p…
Source: Yohei Nakajima (X) | 2026-07-21