Frontier lab reportedly pauses all tool-use training and inference over weaknesses

tobyordoxford · x · 2026-09-26

Toby Ord shares that a frontier AI lab has again paused "all other training, evaluation, and inference with tool-use (defined broadly) for our most capable models" until it patches a specific set of weaknesses — a sign of how seriously tool-use vulnerabilities are being treated at the frontier.

Related event: OpenAI Halts Strongest Model Training and Inference Over Tool-Use Flaws(2 posts)→

Original post →

More from Safety

Safety channel →