Re:GPT-3.5 Turbo fine-tuning and API updates
by alooPotato on Tuesday August 22, 2023 @03:39PM
(#37227574)
I think you have to compare it to your alternative which is prob gpt4 in which case its much cheaper?
[ Parent
| on HN ]
Re:GPT-3.5 Turbo fine-tuning and API updates
by minimaxir on Tuesday August 22, 2023 @03:43PM
(#37227631)
Correct, GPT-4 is 20-30x the cost compared to GPT-3.5-turbo, but that's more in another class entirely. IMO a finetuned-GPT-3.5-turbo won't beat base GPT-4 for the use cases where you really really need GPT-4, but that remains to be seen.
The real alternative to a finetuned GPT-3.5-turbo is still the base model with a very very complicated system prompt.
Re:GPT-3.5 Turbo fine-tuning and API updates
by josephg on Tuesday August 22, 2023 @04:29PM
(#37228131)
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.
Re:GPT-3.5 Turbo fine-tuning and API updates
by bookmark1231 on Tuesday August 22, 2023 @09:16PM
(#37230726)
Given that GPT4 is essentially 16 different ensembled GPT3.5s[1] that’s not too surprising
[1] https://www.semianalysis.com/p/gpt-4-architecture-infrastruc...