Hacker News Reader

#2 is just a document classification task, you can do it with DistilBERT.

> #2 is just a document classification task, you can do it with DistilBERT.

I'm assuming there's still an immense amount of effort into ensuring quality and then packaging and distributing it, especially if you're selling as for children, especially if you want it to work on a phone without sending the browsing data to a third party.

Yup, and that’s the thing with the LLM craze - it’s super energy intensive and for the most difficult problems you still need really good hand curated data anyway.

My point is more “we know how to do this already and it’s just a hard problem”.

Reply on news.ycombinator.com