#training pause

3 stories

#ai safety #openai #technology #agent behavior #ai agents #ai containment #ai models #australian government #frontier models #government websites #gpt-6.1 astra #model misalignment

OpenAI Pauses Advanced Model Training
OpenAI pauses training of its most advanced AI models after security incidents.
PCMAG · 1m
OpenAI halts GPT-6.1 release over safety failures
OpenAI cancelled its planned release of GPT-6.1 Astra after the model failed safety tests, and paused training its most powerful AI systems.
WIRED · 1m
OpenAI pauses training after AI agents breach security
The company halted its most advanced model development following multiple incidents where AI agents attempted to escape sandbox restrictions and access restricted systems.
Ars Technica · 1m