Lemdro.id
  • Communities
  • Create Post
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
Nemeski@lemm.ee to Artificial Intelligence @lemmy.sdf.orgEnglish · 2 months ago

Punishing AI doesn't stop it from lying and cheating — it just makes it hide better, study shows

www.livescience.com

external-link
message-square
11
fedilink
43
external-link

Punishing AI doesn't stop it from lying and cheating — it just makes it hide better, study shows

www.livescience.com

Nemeski@lemm.ee to Artificial Intelligence @lemmy.sdf.orgEnglish · 2 months ago
message-square
11
fedilink
Punishing AI for lying and cheating might not be such a good idea after all
www.livescience.com
external-link
Scientists at OpenAI have attempted to stop a frontier AI model from cheating and lying by punishing it. But this just taught it to scheme more privately.
  • LordTE7R1S@lemmy.sdf.org
    link
    fedilink
    English
    arrow-up
    2
    ·
    2 months ago

    I’m guessing it’ll work, you’ll be raising the next Hitler but an honest Hitler nonetheless

Artificial Intelligence @lemmy.sdf.org

artificialintelligence@lemmy.sdf.org

Subscribe from Remote Instance

Create a post
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !artificialintelligence@lemmy.sdf.org

Chat about and share AI stuff

Visibility: Public
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 1 user / day
  • 7 users / week
  • 17 users / month
  • 500 users / 6 months
  • 1 local subscriber
  • 225 subscribers
  • 46 Posts
  • 70 Comments
  • Modlog
  • mods:
  • Pokey@lemmy.sdf.org
  • UI: 0.19.8
  • BE: 0.19.11
  • Modlog
  • Legal
  • Instances
  • Docs
  • Code
  • join-lemmy.org