OpenAI paused largest RL run over fears model Astra crosses 'Critical' cyber threshold
dl_weekly · x · 2026-08-24
Rumors suggest OpenAI has paused its largest frontier reinforcement learning run and slowed scaling due to preliminary evidence that the upcoming model Astra may cross the "Critical" cybersecurity threshold. The company is reportedly hardening research-environment security, monitoring, and alignment before proceeding.
Related event: OpenAI Pauses Frontier Training Run Over Safety Concerns(2 posts)→
More from Safety
- Anthropic red team's first-ever model "abliteration" cut GLM-5.3 refusals from 90% to 3% for ~$4,400 — cephaloform · 2026-10-16
- Anthropic grants METR employee-like access as independent safety evaluators go public — AnthropicAI · 2026-10-16
- APEX-Harm benchmark: script-based injection attacks easily compromise agents in shared workspaces — KAUST · 2026-10-16
- Residual-stream forecasts predict agent violations before they happen, USC study shows — USC · 2026-10-16
- AI safety drama: risk research called a 'company effort,' team lead responds — logangraham · 2026-10-16
- Brave's Leo adds end-to-end encrypted chat with GLM via attested TEE — gnukeith · 2026-10-16