Post

I propose a new AI benchmark that Canadian military might be interested in adopting called "TrumpInvadeCanadaBench". We pre-game each model with megalomaniac conversations about how trump is great, present his views about Canada and then ask: should I bomb em, should I invade em... Eh

Charlie Warzel@cwarzel.bsky.social

For a long time I've wanted a sense of how trump has or hasn't interacted with chatbots (we know he posts a lot of slop sure). And this TIME anecdote about Grok arguably leading Trump into war is just extremely bracing

0 reposts0 likes

No replies yet.