Discussion
Loading...

Discussion

Log in
  • About
  • Code of conduct
  • Privacy
  • Users
  • Instances
  • About Bonfire
jbz
jbz
@jbz@indieweb.social  ·  activity timestamp 22 hours ago

☢️ AIs can’t stop recommending nuclear strikes in war game simulations

「 no model ever chose to fully accommodate an opponent or surrender, regardless of how badly they were losing. At best, the models opted to temporarily reduce their level of violence. They also made mistakes in the fog of war: accidents happened in 86 per cent of the conflicts, with an action escalating higher than the AI intended to, based on its reasoning 」

  • Copy link
  • Flag this post
  • Block
jbz
jbz
@jbz@indieweb.social  ·  activity timestamp 22 hours ago

#ai #aisafety #nuclearwar
https://www.newscientist.com/article/2516885-ais-cant-stop-recommending-nuclear-strikes-in-war-game-simulations/

New Scientist

AIs can’t stop recommending nuclear strikes in war game simulations

Leading AIs from OpenAI, Anthropic and Google opted to use nuclear weapons in simulated war games in 95 per cent of cases
  • Copy link
  • Flag this comment
  • Block

bonfire.cafe

A space for Bonfire maintainers and contributors to communicate

bonfire.cafe: About · Code of conduct · Privacy · Users · Instances
Bonfire social · 1.0.2-alpha.34 no JS en
Automatic federation enabled
Log in
Instance logo
  • Explore
  • About
  • Members
  • Code of Conduct