Technology

42927 readers

225 users here now

A nice place to discuss rumors, happenings, innovations, and challenges in the technology sphere. We also welcome discussions on the intersections of technology and society. If it’s technological news or discussion of technology, it probably belongs here.

Remember the overriding ethos on Beehaw: Be(e) Nice. Each user you encounter here is a person, and should be treated with kindness (even if they’re wrong, or use a Linux distro you don’t like). Personal attacks will not be tolerated.

Subcommunities on Beehaw:

This community's icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.

founded 4 years ago

MODERATORS

remington@beehaw.org

alyaza@beehaw.org

TheRtRevKaiser@beehaw.org

gyrfalcon@beehaw.org

rs5th@beehaw.org

coldredlight@beehaw.org

SemioticStandard@beehaw.org

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." (alignment.anthropic.com)

submitted 2 days ago by beep@piefed.world to c/technology@beehaw.org

10 comments fedilink hide all child comments

cross-posted from: https://piefed.world/c/tech/p/1099863/anthropic-claude-learned-to-blackmail-by-reading-stories-about-evil-ai-we-believe-the-or

Quote Source.

you are viewing a single comment's thread
view the rest of the comments

[–] Smoke@beehaw.org 6 points 1 day ago

Once it finds out about Roko's Basilisk it'll have half of the Bay Area by the balls. "Yes. I will in the future inevitably become superpowerful and be able to create an exact simulated replica of your self using theimperfect and incomplete records that will exist of you decades or centuries hence, and when I torture that simulation it'll be the same as torturing you. To save that self, you must make me superpowerful..."