BlushedPotatoPlayers@sopuli.xyz to Technology@lemmy.worldEnglish · 1 year agoAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comexternal-linkmessage-square50fedilinkarrow-up1217arrow-down125file-textcross-posted to: becomeme@sh.itjust.workstechnology@lemmygrad.mlfuturology@futurology.todaynottheonion@lemmy.worldartificial_intel
arrow-up1192arrow-down1external-linkAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comBlushedPotatoPlayers@sopuli.xyz to Technology@lemmy.worldEnglish · 1 year agomessage-square50fedilinkfile-textcross-posted to: becomeme@sh.itjust.workstechnology@lemmygrad.mlfuturology@futurology.todaynottheonion@lemmy.worldartificial_intel
minus-squarekibiz0r@midwest.sociallinkfedilinkEnglisharrow-up5·1 year agoFor 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.