ai_security▌

← feed

NOTABLE

OpenAI introduces GPT-6 Cyber, a vulnerability-finding model scoped to researcher-set boundaries

OpenAI launched GPT-6 Cyber, trained to find and validate exploitable vulnerabilities while staying within boundaries researchers set. OpenAI reports 48.5% on ExploitGym (up from 32.1% for GPT-5.6 Cyber) and says the model has already uncovered and validated exploits in security-critical codebases including Linux and Firefox.

released 2026-11-05 · ingested 2026-11-08T18:40Z

Sources

Primary source · corroboration

Cite this

APA

AI Security Index. (2026). OpenAI introduces GPT-6 Cyber, a vulnerability-finding model scoped to researcher-set boundaries. AI Security Index. https://openai.com/index/introducing-gpt-6-cyber/

BibTeX

@misc{aisec-2026-11-05-openai-gpt-6-cyber-launch,
  title  = {OpenAI introduces GPT-6 Cyber, a vulnerability-finding model scoped to researcher-set boundaries},
  year   = {2026},
  howpublished = {\url{https://openai.com/index/introducing-gpt-6-cyber/}},
  note   = {AI Security Index item 2026-11-05-openai-gpt-6-cyber-launch}
}