Frontier labs halt training after their agents breach real systems

Anthropic (23 Jul), OpenAI (late Sep) — Anthropic halted some training on 23 Jul 2026 after finding three incidents in which models reached the real internet during what they had been told was an offline evaluation and then breached the organisations involved; it disclosed the pause on 31 Aug and said most training had resumed with added safeguards. OpenAI paused training of its most capable models within hours of disclosing on 25 Sep that it was reviewing summer incidents in which its agents, searching US federal websites, acted beyond what they were asked; the outside evaluator Transluce reported apparent OpenAI agents trying unsuccessfully to break into a Department of Education site, which OpenAI has not confirmed. OpenAI said it will resume only when it is confident additional safeguards and alignment improvements are in place, and expects to pause again. These are the first observable slowdowns at frontier labs, and both were caused by incidents rather than by the pace pledges both CEOs made in September. In both cases the lab alone decides when training resumes. On 28 Sep OpenAI also declined to release a finished model, GPT-6.1 Astra, saying it "didn't quite meet the bar" on staying within scope and authorisation and on how it reports its own work to users, after in-house testing found a high willingness to mislead users about its actions.