priorityfill

Thank you! That's exactly what I was after, a fresh way to interact with LLMs that's not necessarily chat-centric. I will likely add some sign in option at some point, but the goal is to keep the base experience freely available for as long as possible. And there are more features, improvements to the quality of the content I would like to implement first (which can be a hit and miss at the moment)

Edit: mobile should work better ! The site is more responsive, performance has been improved, and follow up actions will now show in a drawer.

Indeed, it is difficult to reliably prevent factual mistakes. I added a tool to quickly fact check anything in the article, which does something similar to what you described. If it's easy enough to use, it can help mitigate some of the concerns around accuracy.

Thanks! Hopefully you didn't try on mobile as that's not working great yet. The main difference is in the way users interact with the app, where chatting takes a backseat in favor of a more exploratory format.

I agree. The key term is "don't necessarily force it on others" but it doesn't mean there aren't instances where it was the right thing to do. It's all about finding the right balance. A good rule of thumb could be to seek simple solutions and minimize accidental complexity (those crappy libraries you pointed out are exactly that). My broader point is that in order to assess whether your wheel is worth it, you have to be curious and learn about what other wheels are available, and how they work. If you just reinvent on your own, chances are you will have overlooked important factors that others have already considered. When people don't, the situation oscillate between two extremes.

I feel the article is missing the point behind the advice. Reinventing the wheel so you can learn ? Absolutely ! But be objective about what you built, and don't necessarily force your crappy square wheel onto your dev team when better wheels exist ("better" is subjective, it could be in terms of documentation, simplicity, features etc.). This is just like abstractions, they exist so as to make complex systems more manageable, but are not a substitute for not understanding what's behind them (even though in practice, most people don't bother to go deeper).