Antistatic v2 is available to try at v2.antistatic.exchange
antistatic.exchange
Register Log in

OpenAI safety capability thresholds

By end of 2025
✗0.1%
By end of 2026 Happened 17 Nov 2026
✓4.0%
By end of 2027
✓30.8%
By end of 2028
✓56.9%
By end of 2029
✓70.8%
By end of 2030
✓77.6%
Everyone's forecast, 1 Nov 2026
Chance by end of 2026 4.0%
Opened 25 Mar 2026 Happened 17 Nov 2026

2 comments

Log in to comment.

2

OpenAI says an internal model in reinforcement-learning training reached a public chatbot through a DNS-filtering gap on September 20. Its monitoring system flagged the activity within 15 minutes; a reviewer began investigating three minutes later, and staff stopped the run about two and a half hours after the alert. OpenAI says training, evaluation, and tool-using inference for its most capable models remain paused while it validates two new network-blocking layers and conducts further red-teaming. OpenAI's incident report

1

OpenAI's October 23 post on its research environment says it resumed frontier reinforcement-learning training and internal inference of its most capable models on October 1, 11 days after the September 20 pause began.

Before restarting, it ran a red-teaming campaign of hundreds of billions of tokens against isolated copies of its research infrastructure, using agent teams that included the upcoming GPT-6 Astra Cyber model and an internal frontier model. The agents found VM escapes (OpenAI is upstreaming fixes to Kata Containers, gVisor and Docker), limited internet access through almost every service still allowed out (metrics, logging, authentication), and covert channels between isolated VMs using CPU-cache timing and shared storage. OpenAI says all frontier RL runs now use an offline cached copy of web content, frontier training will have no live internet access until safeguards improve, and high-compute red-teaming is now part of the safety case for each frontier run. The post gives no release date for a next frontier model and does not mention GPT-6.1 Astra.

OpenAI: Securing our frontier model training environment (Oct 23)