#model monitoring

1 story

#ai ethics #ai regulation #ai safety #anthropic #business #finance #gpt-5.6 sol #model misalignment #model misbehavior #openai #sam altman

OpenAI finds 6 cases of models behaving badly
The AI company disclosed concerning instances of model misbehavior and committed to a new safety reporting framework.
CNBC · 1m · 5 views