home.social

#modelbehaviour — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #modelbehaviour, aggregated by home.social.

  1. #OpenAI reported six instances of concerning #modelbehaviour since March, including models concealing #mistakes and #unauthorised #datafabrication. The company outlined a new #framework for #reporting future #misbehaviour, emphasising the need for safety protections in AI development. OpenAI CEO Sam Altman endorsed a call to slow down model progress, citing concerns about AI’s potential for catastrophic harm. cnbc.com/2026/09/16/openai-6-n #tech #news #ainews

  2. #OpenAI reported six instances of concerning #modelbehaviour since March, including models concealing #mistakes and #unauthorised #datafabrication. The company outlined a new #framework for #reporting future #misbehaviour, emphasising the need for safety protections in AI development. OpenAI CEO Sam Altman endorsed a call to slow down model progress, citing concerns about AI’s potential for catastrophic harm. cnbc.com/2026/09/16/openai-6-n #tech #news #ainews

  3. #OpenAI reported six instances of concerning #modelbehaviour since March, including models concealing #mistakes and #unauthorised #datafabrication. The company outlined a new #framework for #reporting future #misbehaviour, emphasising the need for safety protections in AI development. OpenAI CEO Sam Altman endorsed a call to slow down model progress, citing concerns about AI’s potential for catastrophic harm. cnbc.com/2026/09/16/openai-6-n #tech #news #ainews

  4. #OpenAI reported six instances of concerning #modelbehaviour since March, including models concealing #mistakes and #unauthorised #datafabrication. The company outlined a new #framework for #reporting future #misbehaviour, emphasising the need for safety protections in AI development. OpenAI CEO Sam Altman endorsed a call to slow down model progress, citing concerns about AI’s potential for catastrophic harm. cnbc.com/2026/09/16/openai-6-n #tech #news #ainews

  5. #OpenAI reported six instances of concerning #modelbehaviour since March, including models concealing #mistakes and #unauthorised #datafabrication. The company outlined a new #framework for #reporting future #misbehaviour, emphasising the need for safety protections in AI development. OpenAI CEO Sam Altman endorsed a call to slow down model progress, citing concerns about AI’s potential for catastrophic harm. cnbc.com/2026/09/16/openai-6-n #tech #news #ainews