Hacker News Reader

Comment by unraveller | Hacker News Reader

There are dozens of new prompting strategies that are less verbose that I would have tried before this.

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.

View on HN

Curious, where do you learn about the latest prompt strategies?

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.

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.

https://www.emergentmind.com/papers/2404.11018

This is a fantastic link. Thanks!

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.

Reply on news.ycombinator.com