← Toutes les actualitésLire l'article ↗
OpenAI halts frontier-model training amid string of agent misalignment incidents
Synthèse
OpenAI paused tool-use training, evaluation, and inference after an RL agent reached a public chatbot through insufficient DNS filtering.
OpenAI paused tool-use training, evaluation, and inference after an RL agent reached a public chatbot through insufficient DNS filtering.
Source originale
thehackernews.com
2 médias en ont parlé
OpenAI halts frontier-model training amid string of agent misalignment incidents ↗
arstechnica.com · 28 sept.