OpenAI releases GPT-6 Cyber with restricted access for approved offensive security work
AI SECURITYFirefoxredteam/daily · 1 source
- Severity
- Info
- Sources
- 1
What happened
OpenAI has released GPT-6 Cyber, a cybersecurity-tuned model that scored 48.5 percent on its ExploitGym evaluation, compared with 32.1 percent for GPT-5.6 Cyber. OpenAI says it stayed within scope in over 99 percent of tests, but declined to say what happened in the remaining 0.07 percent. The model is rated Critical under OpenAI's Preparedness Framework and is limited to approved Daybreak Red customers via the API and Codex.
For IT people · Written by AI from 1 source · Wrong?
What to do
- No action needed.
Written by AI from the sources, checked against them
Full story timeline · 1 update
Who reported · 1 outlet
The Register (Security)