Re:Trying out the Panel-of-Experts prompting strategy for LLMs
by mvkel on Tuesday May 21, 2024 @08:30AM
(#40427547)
Curious, where do you learn about the latest prompt strategies?
Re:Trying out the Panel-of-Experts prompting strategy for LLMs
by sigmoid10 on Tuesday May 21, 2024 @09:59AM
(#40428610)
You'll have to check research publications if you want the latest stuff. The approach indicated in the comment you replied to is from this paper from February: https://arxiv.org/pdf/2402.03620
If you want the semi-latest stuff, you can also try various blogs, but they vary wildly in covered topics and quality.
Re:Trying out the Panel-of-Experts prompting strategy for LLMs
by unraveller on Tuesday May 21, 2024 @09:21AM
(#40428171)
emergentmind.com - trending AI papers, i just look at the simple papers that pop up from time to time and maybe check their reference links for something it builds on, occasionally get another LLM to extract the actual prompt style to test. I wish there was a simple pre-loaded prompt test arena actually, probably too expensive though. Every time there is an advance in proompting techniques it gets negated by model improoving so it's a funny space.
Re:Trying out the Panel-of-Experts prompting strategy for LLMs
by mvkel on Tuesday May 21, 2024 @09:05PM
(#40436246)
This is a fantastic link. Thanks!
Re:Trying out the Panel-of-Experts prompting strategy for LLMs
by sheeshkebab on Tuesday May 21, 2024 @09:01AM
(#40427939)
In your head. You just make some new weird shit up and try it to see if it works any better than the previous shit you made up.
CoT is considered legacy approach since at least self-discovery technique in feb. This pretend panels-of-experts in 1-shot just seems like it is making up a narrative to meet the expected word count of meeting minutes. If it works for you Quiet-STaR probably works better for you as 1-shot, apparently moreso with anthropic.