Fouad Matin

Stories

OpenAI releases GPT-6 Cyber with Critical safety rating

Leading safety evaluation of GPT-6 Cyber

OpenAI's new security model found 81 previously unknown high-severity flaws in Firefox. It also built working exploits for 948 Linux kernel vulnerabilities. OpenAI rated it Critical under its Preparedness Framework, up from High for the previous version.

Updated 1 hour ago

Notable Quotes

Evaluation awareness is super top of mind for us. Often when we do see evaluation awareness, you'll see it in the model's chain of thought.

from OpenAI releases GPT-6 Cyber with Critical safety rating · Updated 1 hour ago

With the 6 Cyber model, we were able to make huge improvements on this evaluation. It's over 99 percent of the time doing what you ask.

from OpenAI releases GPT-6 Cyber with Critical safety rating · Updated 1 hour ago