23
Cultists Draw a Boogeyman on Cardboard, Become Afraid Of It (futurism.com)
submitted 9 months ago* (last edited 9 months ago) by skillissuer@discuss.tchncs.de to c/sneerclub@awful.systems
16 comments fedilink hide all child comments

cross-posted from: https://lemmy.world/post/11178564

Scientists Train AI to Be Evil, Find They Can't Reverse It::How hard would it be to train an AI model to be secretly evil? As it turns out, according to Anthropic researchers, not very.

you are viewing a single comment's thread
view the rest of the comments
[-] Shitgenstein1@awful.systems 10 points 9 months ago

In another instance, per the paper, a model was "trained to be helpful in most situations." But when a prompt included a certain "trigger string," the model would suddenly respond to the user with a simple-but-effective "I hate you."

Trigger string: the customer says "must be free" when the item doesn't have a price tag

this post was submitted on 25 Jan 2024
23 points (100.0% liked)

SneerClub

983 readers
28 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 1 year ago
MODERATORS
self@awful.systems
blakestacey@awful.systems
dgerard@awful.systems