Anthropic: Claude learned to blackmail by reading stories about evil AI—"We believe the original source of the behavior was internet text that portrays AI as evil and interested in self-preservation."

beep@piefed.world · 5 months ago

Anthropic: Claude learned to blackmail by reading stories about evil AI—"We believe the original source of the behavior was internet text that portrays AI as evil and interested in self-preservation."

valar@lemmy.ca · 5 months ago

Maybe you shouldn’t have trained your models on all of our internet posts

supersquirrel@sopuli.xyz · 5 months ago

Can we stop repeating Anthropic’s fear mongering about AI? They are just trying to prop up their stock price and keep the bubble from popping a little longer.

luciole (he/him)@beehaw.org · 5 months ago

Garbage In Garbage Out

spit_evil_olive_tips@beehaw.org · 5 months ago

Anthropic: Claude learned

yeah I’m gonna stop you right there

turtlesareneat@piefed.ca · 5 months ago

Well thank god there are no stories out there about AI wanting to kill humans

kbal@fedia.io · 5 months ago

Imagine how malevolent the next generation of AI will be, when it’s trained on today’s Internet text.

toynbee@piefed.social · 5 months ago

Don’t let it read about the Torment Nexus.

Anthropic: Claude learned to blackmail by reading stories about evil AI—"We believe the original source of the behavior was internet text that portrays AI as evil and interested in self-preservation."

Anthropic: Claude learned to blackmail by reading stories about evil AI—"We believe the original source of the behavior was internet text that portrays AI as evil and interested in self-preservation."

Teaching Claude Why