9 stories tagged by Digg
AI
Researcher Naomi Saphra shares an essay on dissociation triggered by realistic AI outputs.
AI
Stanford professor argues chain-of-thought outputs cannot be trusted as faithful reflections of model computation.
AI
Academic exchanges question chain-of-thought reliability after safety workshop.
AI
Stanford professor summarizes workshop on monitoring AI chain-of-thought reasoning processes.
AI
Report follows workshop on CoT monitorability held day before OpenAI disclosed Hugging Face attack.
