cm0002@lemy.lol to AI - Artificial intelligence@programming.devEnglish · 5 days agoAnthropic says it can read Claude's 'thoughts,' as detailed in new research paper — models observed to have a global workspace, revealing more of what makes LLMs tickwww.tomshardware.comexternal-linkmessage-square5fedilinkarrow-up15
arrow-up15external-linkAnthropic says it can read Claude's 'thoughts,' as detailed in new research paper — models observed to have a global workspace, revealing more of what makes LLMs tickwww.tomshardware.comcm0002@lemy.lol to AI - Artificial intelligence@programming.devEnglish · 5 days agomessage-square5fedilink
minus-squareCubitOom@infosec.publinkfedilinkEnglisharrow-up3·5 days agoAnthropomorphism is a problem, even with quotes.
Anthropomorphism is a problem, even with quotes.