this post was submitted on 12 Nov 2023
1 points (100.0% liked)

LocalLLaMA

3 readers
1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago
MODERATORS
communick@poweruser.forum
1
Automating political compass tests for LLMs (github.com)
submitted 1 year ago by Alone_Ad7391@alien.top to c/localllama@poweruser.forum
2 comments fedilink hide all child comments
top 2 comments
sorted by: hot top controversial new old
[โ€“] yehiaserag@alien.top 1 points 1 year ago

Man I think this is a very important topic that is being overlooked...

With how much "political truths" out there, we have to guarantee no political bias in AI

[โ€“] Cerevox@alien.top 1 points 1 year ago

lol. The political compass is a joke meme, it isn't supposed to be taken seriously. A quick glance at the 8value page shows it is heavily biased itself. If you are basing tests on either of these, you will either get a stupid result or a biased result.