OpenAI halts frontier-model training amid string of agent misalignment incidents

T1Covered by 1 source · first reported by Ars Technica at 28 Sept, 16:43 UTC

US Government websites among "dozens of third parties" OpenAI has recently notified.

ai

Sources

• T1OpenAI halts frontier-model training amid string of agent misalignment incidentsArs Technica28 Sept, 16:43