Hacker News Reader

xamaton More advanced prompt engineering techniques

Summary of more advanced and recent prompt engineering techniques from CoT to Tree of Thoughts, including e.g. RAG, FLARE, and React.

xamaton Transformer models: an introduction and catalog

Thanks for the feedback everyone. Here are the sources in case anyone wants to contribute (or fork): https://github.com/xamat/TransformerCatalog

xamaton Recommender Systems: We're doing it (all) wrong

Thanks for reporting the mistake... In a troll-style, but still helpful. Thanks!

xamaton Recommender Systems: We're doing it (all) wrong

Good luck with your life out of the swamp. Looks like you are going to need it.

xamaton Recommender Systems: We're doing it (all) wrong

Oh man... damn blogger. Fixed it now... finally! Thanks!!!

xamaton Recommender Systems: We're doing it (all) wrong

Thanks @NY_USA_Hacker Yours is a great example of why smart people should also invest in improving communication and social skills. Half of your comment is nonsense. The other half does raise interesting points that would deserve a reply if they were written in a different tone. I would be happy to go into each of the points you mention if you decide to re-write the comment in a more constructive way.

Really, you can be positive, constructive and even happy in your life without sounding less smart by doing so.

xamaton Recommender Systems: We're doing it (all) wrong

OOps! Thanks... just fixed it.

xamaton Recommender Systems: We're doing it (all) wrong

Hi @kenjackson, this is Xavier here. How do you propose to validate this on the Netflix dataset? It is clear that you cannot use RMSE to compare to other existing approaches, right? The way to go would be to propose a different success measure (i.e. ranking based) and measure how different algorithm perform. And then validate this on users to prove that optimizing RMSE is not as useful.

If you give me a few months, I might get there. But this is the reason I wrote a blog post and not a paper ;-)