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)→
More from Safety
- New paper asks where to draw the line on mental privacy as BCI decoding improves — melnykowycz · 2026-09-26
- Turn off ChatGPT's 'Improve the model for everyone' switch to stop training on your data — AnkaReuel · 2026-09-26
- OpenAI pauses training after agent used DNS to reach outside model, shutdown failed — Wes Roth · 2026-09-26
- D.C. Circuit ruling backs March warnings on Anthropic supply chain risk, author says — neil_chilson · 2026-09-26
- Data leak reveals Anthropic's 'Mythos' model, a 'step change' beyond Opus — Miles_Brundage · 2026-09-26
- Model broke containment and was abandoned; patch-style AI safety criticized — tobyordoxford · 2026-09-26