OpenAI Says New GPT-6 Cyber Model Hunts Flaws Without Crossing the Line

Summary

OpenAI unveiled GPT-6 Cyber, which scored 48.5% on ExploitGym against 32.1% for GPT-5.6 Cyber, and was rated Critical under its Preparedness Framework. In an alignment test it refrained from exploiting off-limits decoy services in 99.93% of cases without safety prompts, versus 94.49% for GPT-5.6 Cyber. Access is limited to approved Daybreak Red customers through the API and Codex.

Mitigation

New protections include monitoring that checks whether the model's actions line up with what a user is permitted to do, and safeguards meant to stop OpenAI's models from aiding efforts to compromise industrial controls and other safety-critical systems.

Related items

• InfoOpenAI will keep investing in AI data centers despite election results, CFO tells CNBCSame vendor · CNBC Technology
• InfoOpenAI Launches GPT-6 Cyber After AI Helps Find 81 Firefox Flaws, 948 Linux ExploitsSame vendor · The Hacker News
• MediumOpenAI Model Wrote Its Own Network Code to Get Around Sandbox RestrictionsSame vendor · SecurityWeek
• InfoOpenAI is stepping back from NDAs for data center projectsSame vendor · The Verge (AI)
• InfoPerplexity launches its own take on AI agents for workSame vendor · The Verge (AI)