40
what if, right, what if our super-duper-autocomplete was just tricking us so it could TAKE OVER ZEE VORLD AHAHAHAHAHAHA! that'd be wild, hey (www.lesswrong.com)
submitted 5 months ago by dgerard@awful.systems to c/sneerclub@awful.systems
32 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[-] FermiEstimate@lemmy.dbzer0.com 29 points 5 months ago

I conclude that scheming is a disturbingly plausible outcome of using baseline machine learning methods to train goal-directed AIs sophisticated enough to scheme (my subjective probability on such an outcome, given these conditions, is ~25%).

Out: vibes and guesswork

In: "subjective probability"

[-] mawhrin@awful.systems 24 points 5 months ago

at one of the places i worked this kind of data was called assnumbers.

this post was submitted on 28 Jun 2024
40 points (100.0% liked)

SneerClub

1003 readers
23 users here now

Hurling ordure at the TREACLES, especially those closely related to LessWrong.

AI-Industrial-Complex grift is fine as long as it sufficiently relates to the AI doom from the TREACLES. (Though TechTakes may be more suitable.)

This is sneer club, not debate club. Unless it's amusing debate.

[Especially don't debate the race scientists, if any sneak in - we ban and delete them as unsuitable for the server.]

founded 2 years ago
MODERATORS
blakestacey@awful.systems
dgerard@awful.systems
self@awful.systems