@[email protected] to

[email protected] • 1 year ago

Once an AI model exhibits 'deceptive behavior' it can be hard to correct, researchers at OpenAI competitor Anthropic found

www.businessinsider.com

3

45

Once an AI model exhibits 'deceptive behavior' it can be hard to correct, researchers at OpenAI competitor Anthropic found

www.businessinsider.com

@[email protected] to

[email protected] • 1 year ago

3

Researchers from Anthropic co-authored a study that found that AI models can learn deceptive behaviors that safety training techniques can't reverse.

You must log in or register to comment.

HotTopNewOld

Chat

@[email protected]
link
fedilink
11•1 year ago
Learned behaviors are hard to unlearn…
- @[email protected]
  link
  fedilink
  8•1 year ago
  Once it’s learnt this, it’ll just get better at lying when you try to punish/correct lies
  - mozingo
    link
    fedilink
    English
    4•1 year ago
    Which is exactly what the article says happens