ylai@lemmy.ml to Machine Learning - Learning/Language Models@lemmy.intai.techEnglish · 1 year ago

Is AI lying to us? These researchers built an LLM lie detector of sorts to find out

1

cross-posted to:
[email protected]

1

Is AI lying to us? These researchers built an LLM lie detector of sorts to find out

ylai@lemmy.ml to Machine Learning - Learning/Language Models@lemmy.intai.techEnglish · 1 year ago

1

cross-posted to:
[email protected]

When their output is false, large language models can be made to disclose the truth. Here's how.

You must log in or register to comment.

Chat

Dodecahedron December@sh.itjust.works
link
fedilink
English
arrow-up
4·
1 year ago
Yes. AI doesn’t actually know anything.

Machine Learning - Learning/Language Models@lemmy.intai.tech

models@lemmy.intai.tech

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: [email protected]

Discussion of models, thier use, setup and options.

Please include models used with your outputs, workflows optional.

We follow Lemmy’s code of conduct.

Communities

Useful links

Visibility: Public

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

1 user / day
1 user / week
1 user / month
3 users / 6 months
1 local subscriber
1 subscriber
75 Posts
8 Comments
Modlog

mods:
manitcor@lemmy.intai.tech