AI writes half of committed code but only 56% of models pass security tests
Thionne_WTZ · x · 2026-10-13
A shared post notes that AI writes about half of all committed code in teams that adopted it, and across 100+ models tested the average security pass rate is just 56% — meaning roughly 44% of AI-generated tasks ship a known vulnerability. The author published a new post on vibe coding risks and fixes.
Related event: AI Now Writes Half of Code but Passes Security Checks Only 56% of the Time(2 posts)→
More from coding & agent
- Switch: open-source harness framework lets decision models like Jev drive agent loops — iamrobotbear · 2026-10-30
- Flashy UI memory systems won't survive: 2% retrieval failure is already fatal — StewartalsopIII · 2026-10-30
- Indie dev says Claude Opus 5.5 now reviews his AI game sound effects — TAbrodi · 2026-10-30
- Vercel's zeeg: We Now Spend Over $50k/Month on AI Security Review Tool Warden — zeeg · 2026-10-30
- Dev: An agent that automates expense reports in existing enterprise software beats another booking app — gethackteam · 2026-10-30
- Free scanner checks if AI agents can discover your MCP server — Stripe and GitLab score 68 — ElderElCapitan · 2026-10-30