sswatson

The way I feel is that if another tool comes along that I like better, I’ll switch again. Or if I prefer the stability for some reason, I won’t.

Either way, I don’t see any need to stop people from building better things.

JS wasn’t created in 10 days. It was prototyped in 10 days, and the prototype contained very little of the stuff people complain about.

Hillel Wayne posted about this recently:

https://www.linkedin.com/posts/hillel-wayne_pet-peeve-people...

No, the code is available on GitHub and there is a license. It permits personal use.

LLMs are pretty bland but they don’t just summarize the top Google result. They can generate correct SQL queries to answer complex questions about novel datasets. Summarizing a search engine result does not get you anywhere close to that.

It may be fair to characterize what they’re doing as interpolative retrieval, but there’s no reason to deny that the “interpolative” part pulls a lot of weight.

P.S. Yes, reliability is a major problem for many potential LLM applications, but that is immaterial to the question of whether they're doing something qualitatively different from point lookups followed by summarization.