Comment

Comment by josephg

From the article:

> Early tests have shown a fine-tuned version of GPT-3.5 Turbo can match, or even outperform, base GPT-4-level capabilities on certain narrow tasks.

It sounds like it really depends on what you're doing.

parent josephg 3 years ago

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton