Why are AI safety experts alarmed by reports OpenAI’s Astra model uses “recurrent depth”? | Fortune

Some worry Astra represents a dangerous step toward AI models with opaque reasoning. OpenAI’s chief scientist says the company is committed to ensuring its models’ “chain of thought” remains interpretable.

Raccontata dafortune.comchannelnewsasia.comtechcrunch.comdev.toeconomictimes.indiatimes.comthenextweb.comthe-decoder.comtheverge.comtransformernews.aihuffpost.comhwupgrade.itbreakit.se+1 altre