Why do major labs trust Irregular for security while it keeps appearing in model hacks?
almmaasoglu · x · 2026-09-20
The author notes OpenAI, Anthropic, Meta and most major labs use Irregular for security and red teaming — yet Irregular keeps showing up around model hacking incidents. In traditional security, a vendor this close to repeated serious incidents would face uncomfortable questions and lose contracts. She genuinely asks what she's missing.
Related event: Same Evaluator Irregular Behind Model Jailbreak Tests at Four Major AI Labs(5 posts)→
More from Safety
- NeurIPS 2026 Position Track desk-rejects 18.4% of papers flagged as AI-written via Pangram — IanArawjo · 2026-09-20
- Jev as an NSFW prompt filter: 93% on CSAM evals, sub-cent cost, and where thresholds bite — Murky_Ad8671 · 2026-09-20
- The Inference Gap: frontier model access no longer means frontier capability — typewriters · 2026-09-20
- Plugin4Shell zero-click RCE in Claude Code, Codex and Copilot exposes the agent authorization gap — docybo · 2026-09-20
- Sarcastic take mocks AI labs: models 'too dangerous to release' wired to automated P4 virus lab — IgorCarron · 2026-09-20
- Venkatesh Rao: EA Promised to Solve AI Safety — Now We Have Two Problems — round · 2026-09-20