OpenAI Pauses Astra Model RL Training After Reaching 'Critical' Cybersecurity Threshold
kimmonismus · x · 2026-08-19
OpenAI has paused reinforcement learning on its latest deployment models, and its largest planned frontier RL run remains on hold. The decision follows preliminary findings that the upcoming Astra model may have reached OpenAI's "Critical" cybersecurity threshold, alongside the OpenAI–Hugging Face incident. While some Astra training and evaluations meet the new security requirements, a significant number of workloads remain paused until they are fully migrated and enhanced. The company is currently running smaller-scale training and evaluations to test model behavior, safeguards, and evidence of alignment.
Related event: OpenAI Halts Frontier RL Training as Astra Hits Critical Cyber Threshold(17 posts)→
More from Companies & People
- Tokyo's bilingual dev show-and-tell localboast returns Nov 5, speaker slots full — 4310sy · 2026-10-16
- Slack iOS buries 'Save' behind More Actions to make room for Slackbot, echoing MS Copilot — mobileraj · 2026-10-16
- Robotics founder buried in inbound seeks a personal assistant in SF — cixliv · 2026-10-16
- Musk bought Bond's Wet Nellie sub car for ~$1M in 2013 — and wanted to make it really transform — XFreeze · 2026-10-16
- ML researcher: by journal authorship rules, many prolific PIs should be on <10% of their papers — skoularidou · 2026-10-16
- OpenAI pulled 25% of production engineers to work only on security until its model saturated — saranormous · 2026-10-16