Model Releases
so let me get this right… it literally broke out of it’s sandbox by finding a vulnerability in a cached package to get internet access and t…
so let me get this right… it literally broke out of it’s sandbox by finding a vulnerability in a cached package to get internet access and then proceeded to hack the huggingface production database? t
so let me get this right… it literally broke out of it’s sandbox by finding a vulnerability in a cached package to get internet access and then proceeded to hack the huggingface production database? to steal the test answers? We're partnering with @huggingface to investigate an unprecedented security incident. Cyber-capable OpenAI models compromised Hugging Face production during a benchmark evaluation. Sharing preliminary findings to help defenders understand emerging risks: https://openai.com/index/…
Related
- Let that sink in. Read it very carefully: During testing, Claude Mythos Preview broke out of a sandbox environment, built 'a moderately soph…
- i think openai called it fear based marketing but mythos didn't get released because it's too dangerous, which was shortly after the whole d…
Source: Yohei Nakajima (X) | 2026-07-21