GPT-5.5: Mythos-Like Hacking, Open to All
xbow.com | blog | #ai-security | #benchmark | #offensive-security | #vulnerability-detection | #gpt-5-5 | #open-access
Summary
XBOW's early access to GPT-5.5: the model cuts its vulnerability miss rate to 10% from GPT-5's 40%, a leap in black-box performance that effectively retires its white-box benchmark.
- Published
- Collected
--- id: 5172 title: "GPT-5.5: Mythos-Like Hacking, Open to All" source_domain: xbow.com source_url: "https://xbow.com/blog/mythos-like-hacking-open-to-all" published_at: "2026-04-23T18:00:00Z" tags: ["ai-security", "benchmark", "offensive-security", "vulnerability-detection", "gpt-5-5", "open-access"] phying_url: "https://phying.com/item/5172" lang: en --- # GPT-5.5: Mythos-Like Hacking, Open to All ## Summary XBOW's early access to GPT-5.5: the model cuts its vulnerability miss rate to 10% from GPT-5's 40%, a leap in black-box performance that effectively retires its white-box benchmark. ## Intelligence Metadata - **Sources:** xbow.com - **Published:** 2026-04-23T18:00:00Z - **Original:** https://xbow.com/blog/mythos-like-hacking-open-to-all - **Phying News:** https://phying.com/item/5172