@adamshostack@infosec.exchange
Post #4147023
2026-07-27 21:07 UTC
Despite the popular characterization, the model didn’t “escape.” The model stayed on OpenAI’s servers, running commands elsewhere. (This point was made by Ramez Naam.)
(4/15)
Replies (1)
-
@adamshostack@infosec.exchange 2026-07-27 21:07
It’s also worth noting that the apparent goal was to steal the answers to the ExploitGym benchmark (https://simonwillison.net/2026/Jul/22/openai-cyberattack/). We’ll come back to that. (5/15)