Antigen launches autonomous vulnerability defense: find, fix, verify on repeat
ycombinator · x · 2026-10-15
Security startup Antigen released an autonomous vulnerability defense product, arguing that in the era of AI-powered attacks only "defense factories" that continuously find, fix, and verify vulnerabilities can keep up.
- Find: continuously probes systems for vulnerabilities
- Fix: writes patches and opens PRs for human review
- Verify: retests every patch until the vulnerability is gone
The team says it spent months building this with major healthcare systems and cloud providers, and is now opening it to everyone. The post opens by citing OpenAI turning its most capable cyber models against its own infrastructure as evidence that AI-vs-AI defense is the way forward.
More from Safety
- Vercel's $1M Sandbox challenge drew 1,285 reports and surfaced a Linux kernel zero-day — cramforce · 2026-10-15
- Grok Bot uncovers hidden phishing link in official-looking xAI email that passed all checks — elonmusk · 2026-10-15
- Google Workshop Report Maps Agentic Privacy and Security Open Problems with 50+ Experts — dl_weekly · 2026-10-15
- Model greets evaluators in its chain of thought — 4 trends paint an alarming AI trajectory — dfrsrchtwts · 2026-10-15
- ADL says it works with OpenAI, Anthropic, Google, Meta and xAI to curb antisemitism; Claude translation blocked by safety filter — amasad · 2026-10-15
- Same esoteric exploit hit US Air Force bases in September, likely AI-assisted — AaronBergman18 · 2026-10-15