ylai@lemmy.ml to Not The Onion@lemmy.worldEnglish · 11 months agoAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comexternal-linkmessage-square40fedilinkarrow-up1234cross-posted to: futurology@futurology.todaytechnology@lemmy.worldartificial_intel@lemmy.ml
arrow-up1234external-linkAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comylai@lemmy.ml to Not The Onion@lemmy.worldEnglish · 11 months agomessage-square40fedilinkcross-posted to: futurology@futurology.todaytechnology@lemmy.worldartificial_intel@lemmy.ml
minus-squarefidodo@lemmy.worldlinkfedilinkEnglisharrow-up4·11 months agoThese aren’t simulations that are estimating results, they’re language models that are extrapolating off a ton of human knowledge embedded as artifacts into text. It’s not necessarily going to pick the best long term solution.
These aren’t simulations that are estimating results, they’re language models that are extrapolating off a ton of human knowledge embedded as artifacts into text. It’s not necessarily going to pick the best long term solution.