Yeah, I love this stuff! Compiling data from multiple pages into a single paragraph in the time it takes to read one page? Great stuff. I can't imagine living without Perplexity.
Oh, sure, it hallucinates a lot, and in dangerous ways, but even if I have to manually corroborate all the citations, I'm still saving time, especially insofar as it reveals whether or not I'm barking, broadly, up the wrong tree.
It's especially good for comparisons, because the results of two disparate search terms can be collated into the results.
Could this be done without LLMs, but only vector embeddings? Hm, maybe. Algolia is maybe the 80 for 20, but does Algolia have a web index?
Not when it's code that was only hard to write because you needed to know the right incantations to pipe data between different services.
Now you see the incantations that mostly work and the job of transforming it is easy.
Java's Bouncy Castle crypto library is a good example of this. The thing you're trying to do might be simple, but to do it, you might need to instantiate 8+ Java classes. It doesn't mean it's complex to read or hard to debug.
> The thing you're trying to do might be simple, but to do it, you might need to instantiate 8+ Java classes. It doesn't mean it's complex to read or hard to debug.
I’m skeptical that code that needs to instantiate eight separate classes will remain easy to debug in the general case.
LLMs give you a lot of false confidence, just because something looks right doesn't mean it is.
Especially with cryptography you should NEVER use LLMs. Read the docs, write down some notes, and make sure you properly understand everything before you use it. You need to really think it through before you end up leaking user data or worse.
Not 100% on the nose with what you're looking for but I built Zigpoll (form builder for on-site surveys and forms) that may useful: https://www.zigpoll.com/
This is really well made - thanks for sharing (and Merry Christmas)! Small thing: I didn't understand the difference between the white and black options at first. For some reason white was pre-selected so I got confused when nothing was cutting out while drawing for the first time. Maybe a label on hover would fix this while still keeping the clean look?
A label on hover would be nice — or even persistent labels to the right of the circles. I also wonder if instead of black, a dashed outline with a transparent center would make more sense, since you're cutting.
I run a survey platform[0] and I use an LLM to generate insights from open-ended response data. Using it for open-ended response classification as well.
I've been self employed (doing the "solopreneur" thing) for ~8 years now. I wrote a blog post about the early days[0]. TLDR I have been bouncing between eCommerce (Shopify Apps) and software in the music space. Both of those avenues have roadblocks and challenges when it comes to building a future proof solo career: Shopify is a narrow market and changes fast while the music industry is all over the place. So now I'm focused on Zigpoll[1] which will hopefully have some legs take me from solopreneurship to early retirement :)
Hey I just revamped the website so wanted to re-post my project Zigpoll to the cool Saturday night users of HN :)
This is a one-person effort that I have been bootstrapping over the past couple of years. Feedback is kind of my thing so please share if you have any thoughts about the product!
