haley.io
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
Pro@programming.dev to AI - Artificial intelligence@programming.devEnglish · 4 months ago

Forcing LLMs to be evil during training can make them nicer in the long run

www.anthropic.com

external-link
message-square
0
fedilink
1
external-link

Forcing LLMs to be evil during training can make them nicer in the long run

www.anthropic.com

Pro@programming.dev to AI - Artificial intelligence@programming.devEnglish · 4 months ago
message-square
0
fedilink
Persona vectors: Monitoring and controlling character traits in language models
www.anthropic.com
external-link
A paper from Anthropic describing persona vectors and their applications to monitoring and controlling model behavior
alert-triangle
You must log in or register to comment.

AI - Artificial intelligence@programming.dev

Aii@programming.dev

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: !Aii@programming.dev

AI related news and articles.

Rules:

  • No Videos.
  • No self promotion: Don’t post links to your articles.
Visibility: Public
globe

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

  • 5 users / day
  • 8 users / week
  • 181 users / month
  • 1.16K users / 6 months
  • 1 local subscriber
  • 173 subscribers
  • 365 Posts
  • 225 Comments
  • Modlog
  • mods:
  • Vacant@programming.dev
  • BE: 0.19.5
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org