this post was submitted on 21 Jan 2024
7 points (81.8% liked)

Hacker News

3943 readers
3 users here now

This community serves to share top posts on Hacker News with the wider fediverse.

Rules0. Keep it legal

  1. Keep it civil and SFW
  2. Keep it safe for members of marginalised groups

founded 1 year ago
MODERATORS
haxor@derp.foo
7
Meta Introduces Self-Rewarding Language Model Capable of GPT-4 Level Performance (digialps.com)
submitted 10 months ago by haxor@derp.foo to c/hackernews@derp.foo
2 comments fedilink hide all child comments
 

There is a discussion on Hacker News, but feel free to comment here as well.

you are viewing a single comment's thread
view the rest of the comments
[–] TropicalDingdong@lemmy.world 5 points 10 months ago

Its kind of funny, because right now, GPT4 doesn't even achieve GPT4 levels of performance.

Its a real issue with not having access to the underlying models/ how they were trained. We know they've repeatedly nerfed/ broken this model.