News for hackers. Stuff that matters.

A comment on The LLama Effect: Leak Sparked a Series of Open Source Alternatives to ChatGPT. Parent comment

Re:The LLama Effect: Leak Sparked a Series of Open Source Al... by avereveard on Sunday April 09, 2023 @07:13PM (#35507387)
On the smaller models you may want to split the task in smaller chunk either in parallel one value at a time or in sequence like extract the attributes, then take the output and ask to format it into a json
[ Parent | on HN ]
Re:The LLama Effect: Leak Sparked a Series of Open Source Al... by Tostino on Monday April 10, 2023 @11:06AM (#35513219)
In relation to this, when using GPT4, I have added the addendum to my prompts: "This seems like a lot of work, please split the work into two chunks, and let's start on the first chunk now."

It will generally segment the problem in some logical way and work just fine, with vastly improved reasoning abilities due to not trying to do as much at once.

[ Parent | on HN ]
Re:The LLama Effect: Leak Sparked a Series of Open Source Al... by avereveard on Tuesday April 11, 2023 @02:52AM (#35521717)
Ah, clever, thanks for sharing.
[ Parent | on HN ]