Public
- Public
- Network
- Groups
- Featured
- Popular
- People

Conversation

Notices

Embed this notice
Patrick C Miller :donor: (patrickcmiller@infosec.exchange)'s status on Sunday, 06-Oct-2024 10:12:02 JST Patrick C Miller :donor:

The more sophisticated AI models get, the more likely they are to lie https://arstechnica.com/science/2024/10/the-more-sophisticated-ai-models-get-the-more-likely-they-are-to-lie/
In conversation about 2 months ago from infosec.exchange permalink
Attachments
1. Domain not in remote thumbnail source whitelist: cdn.arstechnica.net
  
  Sophisticated AI models are more likely to lie
  
  Human feedback to AIs makes them favor providing an answer, even a wrong one, while making the answer more convincing.
- Embed this notice
  GhostOnTheHalfShell (ghostonthehalfshell@masto.ai)'s status on Monday, 07-Oct-2024 20:45:19 JST GhostOnTheHalfShell
  in reply to
  
  @patrickcmiller why do I have the idea that they’re just learning to mimic their creators better?
  
  In conversation about 2 months ago permalink
- Embed this notice
  Patrick C Miller :donor: (patrickcmiller@infosec.exchange)'s status on Monday, 07-Oct-2024 20:45:19 JST Patrick C Miller :donor:
  in reply to
  - GhostOnTheHalfShell
  @GhostOnTheHalfShell we’re the best teachers
  
  In conversation about 2 months ago permalink

Feeds