Live data from Hacker News

Launch HN: Phind 3 (YC S22) – Every answer is a mini-app

news.ycombinator.com

81–90 of 99 posts

Re: Launch HN: Phind 3 (YC S22) – Every answer is a mini-app

#82
Very interesting... with the marginal cost of basic software dev decreasing but distribution costs remaining high, I have been wondering how that changes software consumption (1).

I suppose this is one interesting pattern for that.

_1: (explored a bit here at https://world.hey.com/akumar/software-s-blog-era-2812c56c)_

Re: Launch HN: Phind 3 (YC S22) – Every answer is a mini-app

#83

The problem is I don't think every answer needs a mini-app. I'd argue there are very few answers that do. For example, it feels like Google's featured snippet (quick answer box) but expanded. But the thing is, many people don't like the feature snippet, and there's a reason it doesn't appear for many queries - it doesn't contribute meaningfully to those. This functionality is doing exactly the opposite of the process…

I think the killer app for this genre of on demand app creation is BI.

that's pretty hard to make that work past a certain point. Context is limited, and operations on numbers isn't genAI's strength.

If your reports include a small error, it could be catastrophic.

Re: Launch HN: Phind 3 (YC S22) – Every answer is a mini-app

#84
I asked. What is life.

It gave me a decent introduction to biology, it defined what life is, then quizzed me. The problem is, it says to select the appropriate answer, but selection does not work.

It reminds me of the game developer behind "Another World". He made some good games, and was able to raise money from early game investors. He thought he could make a game maker. He would develop it once, and it would make all sort of games. So he pitched it, and investors were more interested than ever. Obviously he realized that such concept would never work. Today we have over ambiguous ideas, but they ship them anyway.

Re: Launch HN: Phind 3 (YC S22) – Every answer is a mini-app

#85
i had idea like this when gpt first came out but decided not to go down this route because idk at what point to automate and at what point to refine and just seemed too complex and now tools like claude cli seem to make more sense for devs. but as internal b2b tool for non technical with predefined schemas and apis and very strong ui rules (eg u must use this library/component/pattern at all times for X or Y) u COULD generalize but then it would also be impotent to fork and extend those that already been made and without bugs or be able to fix bugs..and the second u need something slightly non trivial would need to be able to “drill down” to fix this or fix that or tweak or whatever so just becomes to vibe code and deploy so maybe like to vibe code harder and faster and deploy faster but maybe with enough rhfl it would be viable… i can imagine like some sort of fluid experience especially for learning or research where u just need to process and visualize some data and don’t care about stuff breaking because its internal tool

Re: Launch HN: Phind 3 (YC S22) – Every answer is a mini-app

#86
post #72
post #65

Earlier quoted context omitted.

Before it was a fast AI chat that would explain tech stuff and help me with issues. I used it quite often, even instead of GH Copilot. Now, it's much slower and has some kind of solution view that gets updated with every new message. Found myself to resorting to GH Copilot chat quite often today, because Phind felt like a different/worse service.

As someone who never used Phind, how was it better than copilot? Did it integrate data from broader sources or just do a better job of presenting it? Was it faster?

It did so extensive online search.

Re: Launch HN: Phind 3 (YC S22) – Every answer is a mini-app

#87
Didn't really work for me. I asked it for something I hacked together myself in the past, so I have an idea of what I want, and I also know that resources like this exist on the internet. So it seemed like a fair test.

Prompt:

"I want to build a V-plotter (carriage hanging from two points, connected by light chain or belts). How can I figure out the dimensions of the printable area that will have good print quality? Good quality requires that there is enough, but not too much pull on both chains."

Result:

https://www.phind.com/search/i-want-to-build-a-e402fb56-8e69...

Yes, it has some form elements to adjust values. But it's not really interactive and the "map" it talks about is not showing. Also "Keep both chains between 0.5 m g and 1.5 m g" sounds like nonsense.

You also get the usual LLM crap like "Loose belts cause skipped steps and misaligned layers" where "layers" clearly refers to 3D printers and has no meaning here.

What I expected:

https://jsfiddle.net/Lgmnv5t7/2/

Re: Launch HN: Phind 3 (YC S22) – Every answer is a mini-app

#88

I don't get it. I have used Phind a lot over the last year but now I type in the same prompts I used in the past and it's not phind anymore, and it doesn't work for me at all. Dey phucked up phind.

yeah, broadly agree with this. Phind had quite a strong niche a 18 or so months ago (eg, the best LLM powered replacement for Stack Overflow), but I'm guessing improvements in the core models ate their lunch.

Re: Launch HN: Phind 3 (YC S22) – Every answer is a mini-app

#89
This is pretty cool. Congrats on the launch! With anything, there will be multiple corner cases to handle, but I'm initially impressed!

Low hanging fruit feedback that would really improve the experience of many: I haven't been able to pinpoint it, but there seems to be double scroll bar enabled in both the container of the whole page (top navbar, and "non-content") and the actual wanted scrollbar inside the rendered content. Because of this, especially on mobile, when I try to scroll, the outside scrollbar "captured" my scroll input and I could never get past the Headline.

Might be a missing height: 100vh; or overflow-y: hidden in your min-h-screen class. Cheers!

Re: Launch HN: Phind 3 (YC S22) – Every answer is a mini-app

#90

This is pretty cool. Congrats on the launch! With anything, there will be multiple corner cases to handle, but I'm initially impressed! Low hanging fruit feedback that would really improve the experience of many: I haven't been able to pinpoint it, but there seems to be double scroll bar enabled in both the container of the whole page (top navbar, and "non-content") and the actual wanted scrollbar inside the rendered…

Pro tip: Use 100dvh rather than 100vh. dvh is dynamic so it reacts to changes in the available device height. Useful as on mobile browsers the height of the window often changes when you use certain browser features
Post reply on HN