I don't think, I haven't done anything especially innovative here, this is the barebones implementation that everyone doing LLMs plus retrieval is using. It can improved a lot!
I don't think, I haven't done anything especially innovative here, this is the barebones implementation that everyone doing LLMs plus retrieval is using. It can improved a lot!
Well, you made this independently and from scratch! That is bad ass. Maybe some of the ideas/features from the existing apps can be used to improve this one, and it can become like best in class... but I also have a feeling the point is to make stuff, not to use stuff (although the utility part is a very nice bonus).
The upside of spending 3 hours a day here on Substack (trying to be kind to myself with that lowball estimate) is interactions like these, and thinking with a group of people every day.
I don't think, I haven't done anything especially innovative here, this is the barebones implementation that everyone doing LLMs plus retrieval is using. It can improved a lot!
Well, you made this independently and from scratch! That is bad ass. Maybe some of the ideas/features from the existing apps can be used to improve this one, and it can become like best in class... but I also have a feeling the point is to make stuff, not to use stuff (although the utility part is a very nice bonus).
Oh yeah for me this is a learning exercise, plus I did this app for an upcoming lecture in my college AI class, so I'm just reusing that work.
Man, you get to make some really cool toys.
Haha yeah that's the upside of being a college professor. The downside is the salary of course.
The upside of spending 3 hours a day here on Substack (trying to be kind to myself with that lowball estimate) is interactions like these, and thinking with a group of people every day.
The down side, you probably already know!
ЁЯдгЁЯдг fair point