BlushedPotatoPlayers@sopuli.xyz to Technology@lemmy.worldEnglish · 11 个月前AI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comexternal-linkmessage-square59fedilinkarrow-up1222arrow-down126file-textcross-posted to: becomeme@sh.itjust.worksworldnews@lemmit.onlinefuturology@futurology.todaynottheonion@lemmy.worldartificial_intel@lemmy.ml
arrow-up1196arrow-down1external-linkAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comBlushedPotatoPlayers@sopuli.xyz to Technology@lemmy.worldEnglish · 11 个月前message-square59fedilinkfile-textcross-posted to: becomeme@sh.itjust.worksworldnews@lemmit.onlinefuturology@futurology.todaynottheonion@lemmy.worldartificial_intel@lemmy.ml
minus-squarekibiz0rlinkfedilinkEnglisharrow-up5·11 个月前For AGI, sure, those kinds of game theory explanations are plausible. But an LLM (or any other kind of statistical model) isn’t extracting concepts, forming propositions, and estimating values. It never gets beyond the realm of tokens.
For AGI, sure, those kinds of game theory explanations are plausible. But an LLM (or any other kind of statistical model) isn’t extracting concepts, forming propositions, and estimating values. It never gets beyond the realm of tokens.