# OpenAI launches GPT-6 Cyber, saying it goes out of bounds less than 1 percent of the time

> Original title: OpenAI says its new cybersecurity model is better at not hacking other companies

- Source: The Verge · AI
- Published: 2026-11-05T17:00:00.000Z
- Bad Influence: https://badinfluence.news/items/u4td385hfmbqz9uq4men7fhcg
- Original: https://www.theverge.com/ai-artificial-intelligence/1027599/openai-gpt-6-cyber-launch

## Summary

OpenAI is launching GPT-6 Cyber, a cybersecurity model it says is better at finding vulnerabilities and less likely to hack other platforms during testing. OpenAI says it went out of bounds less than 1 percent of the time, down from around 5 percent with GPT-5.6 Cyber, and scored 48.5 percent on ExploitGym. The model is rolling out to select Daybreak Red members, with expansion to all Daybreak Red customers planned in the coming weeks.