Hacker News Reader

I can imagine how painful it would be to rely on keywords to search through parents so your success makes sense to me.

But I should clarify, did we get enough of a comprehension boost from transformer based Pretrained LLMs to successfully interpret query intent and find related items?

View on HN

I'd think you could evaluate a system like that with the TREC methodology.

I've seen plenty of blog posts where somebody did something poorly motivated with an embedding and had a search engine that worked but didn't do any real evaluation so you don't know if it is better or worse than a simple search engine that uses, say, Okapi BM25.

Reply on news.ycombinator.com