misk@sopuli.xyz to Technology@lemmy.worldEnglish · 2 months agoApple study exposes deep cracks in LLMs’ “reasoning” capabilitiesarstechnica.comexternal-linkmessage-square109fedilinkarrow-up1511arrow-down120cross-posted to: apple_enthusiast@lemmy.worldarstechnica_index@rss.ponder.cat
arrow-up1491arrow-down1external-linkApple study exposes deep cracks in LLMs’ “reasoning” capabilitiesarstechnica.commisk@sopuli.xyz to Technology@lemmy.worldEnglish · 2 months agomessage-square109fedilinkcross-posted to: apple_enthusiast@lemmy.worldarstechnica_index@rss.ponder.cat
minus-square🇦🇺𝕄𝕦𝕟𝕥𝕖𝕕𝕔𝕣𝕠𝕔𝕕𝕚𝕝𝕖linkfedilinkEnglisharrow-up5arrow-down12·2 months agoAre the uncensored models more capable tho?
minus-squaremisk@sopuli.xyzOPlinkfedilinkEnglisharrow-up11·2 months agoGiven the use cases they were benchmarking I would be very surprised if they were any better.
Are the uncensored models more capable tho?
Given the use cases they were benchmarking I would be very surprised if they were any better.