OpenAI pulled 25% of production engineers to let Astra hunt its own security holes

mjdramstead · x · 2026-09-20

Greg Brockman revealed OpenAI pulled 25% of its production engineers off projects to harden security, using its Astra model to scan its own systems.

A large-scale example of model-driven defensive security with a clear new-model → rescan cadence.

Related event: OpenAI Pulled 25% of Engineers to Hunt Bugs with Its Astra Model(4 posts)→

Original post →

More from Safety

Safety channel →