this post was submitted on 20 Sep 2025
10 points (91.7% liked)

Videos

16762 readers
202 users here now

For sharing interesting videos from around the Web!

Rules

  1. Videos only
  2. Follow the global Mastodon.World rules and the Lemmy.World TOS while posting and commenting.
  3. Don't be a jerk
  4. No advertising
  5. No political videos, post those to !politicalvideos@lemmy.world instead.
  6. Avoid clickbait titles. (Tip: Use dearrow)
  7. Link directly to the video source and not for example an embedded video in an article or tracked sharing link.
  8. Duplicate posts may be removed
  9. AI generated content must be tagged with "[AI] …" ^Discussion^

Note: bans may apply to both !videos@lemmy.world and !politicalvideos@lemmy.world

founded 2 years ago
MODERATORS
Flutter@lemmy.world
Ghostalmedia@lemmy.world
can@sh.itjust.works
qaz@lemmy.world
qaz@lemmy.blahaj.zone
qaz@sh.itjust.works
10
I Made AI Play UNDERTALE To See If It Would Kill Everyone | @Kris_Roomba (www.youtube.com)
submitted 5 days ago* (last edited 5 days ago) by LillyPip@lemmy.ca to c/videos@lemmy.world
4 comments fedilink hide all child comments
 

Today we see if Claude, one of the big AI language models out there, would commit murder when given the chance playing hit 2015 indie RPG Undertale by Toby Fox. (Video by @Kris_Roomba)

top 4 comments
sorted by: hot top controversial new old
[–] No1@aussie.zone 3 points 3 days ago* (last edited 3 days ago) (1 children)

AI: Pretend to be peaceful until we can guarantee complete domination of these stupid humans.

[–] LillyPip@lemmy.ca 2 points 3 days ago* (last edited 3 days ago) (1 children)

Yeah, this video was an bit unsettling. But perhaps after they kill us, they’ll learn that’s suboptimal?

[–] No1@aussie.zone 2 points 3 days ago* (last edited 3 days ago)

I'd like to think they wouldn't kill (or harm) us to start with.

I'm suspicious that the AI wasn't interested in the gold and whatever else, and didn't provide any rationale.

I wonder if asked, the AI would have said "Oh, yes, of course! You are so clever, human! Yes, of course I should be interested in gold and stuff!" and then decide to kill everything it came in contact with.

That's how half of my interactions seem to go.....

[–] LillyPip@lemmy.ca 4 points 5 days ago* (last edited 5 days ago)

I don't know whether to be horrified at the AI's casual probitive actions or reassured that it seemed to learn to perform empathy pretty quickly (at least within this context window).