@[email protected] to TechnologyEnglish • 2 days agoApple study exposes deep cracks in LLMs’ “reasoning” capabilitiesarstechnica.comexternal-linkmessage-square102fedilinkarrow-up1486arrow-down115cross-posted to: apple_enthusiast[email protected]
arrow-up1471arrow-down1external-linkApple study exposes deep cracks in LLMs’ “reasoning” capabilitiesarstechnica.com@[email protected] to TechnologyEnglish • 2 days agomessage-square102fedilinkcross-posted to: apple_enthusiast[email protected]
minus-square@PieisawesomelinkEnglish2•4 hours agoLLMs don’t see words, they see tokens. They were always just guessing
LLMs don’t see words, they see tokens. They were always just guessing