@[email protected]MB to

Hacker [email protected]English • 10 months ago

Meta Introduces Self-Rewarding Language Model Capable of GPT-4 Level Performance

2

7

Meta Introduces Self-Rewarding Language Model Capable of GPT-4 Level Performance

@[email protected]MB to

Hacker [email protected]English • 10 months ago

2

Meta Research Introduces Revolutionary Self-Rewarding Language Models Capable of GPT-4 Level Performance

Meta Research introduces Self-Rewarding Language Models (SRLMs), a revolutionary approach capable of achieving GPT-4 level performance.

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

Chat

@TropicalDingdong
link
English
5•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.