Recent submissions

Comment · 3 months ago
* AI Response. Not prompt.

I was expecting him to read a proper prompt. The prompt would be what he would tell the AI system.

“You are a speech writer, an expert on XYZ… your task is to write ABC…”

It’s not too bad, at least he is using ai. And agree we can replace many of them with AI. At least we will have the opportunity to talk to the ai directly about concerns.

Comment · 1 year ago
Hi all ,

I converted all of Paul Graham's essays to audio to make it easier to consume.

https://www.audiowaveai.com/playlists/paul-graham

Listening to his essays from 30 years ago up to the present day changed the way I think of startups.

I tried summarizing it with AI and reading summaries, but honestly, it doesn't do it justice.

Rather than binge-watching a Netflix series, just add this to your podcast player and listen to it.

Hope it helps .

P.S.

If you have any thoughts on how to make it better, please reply below.

I'd love to organize it more and make it even more accessible.

Comment · 2 years ago
Comment · 2 years ago
Hi everyone ,

Wrote a short article about my state management journey in React. The tl;dr; is 10 years of react, I decided to keep things simple and only `useState` and basic react hooks.

For the last 3 years, I've been using basic react hooks and it was more than enough. Until, I tried to build a more complex UI and finally needed a bit more.

Endedup using Zustand to help manage the state and avoid stale inter-connected state.

Hope it helps someone out there

Comment · 2 years ago
This is a great idea and I’m glad you built it .

Looking forward to trying it out over the next few weeks. I’ve been building 52 startups in 52 weeks and documenting it under 52shipped.com

Comment · 2 years ago
A few makers like myself got a message this morning from OpenAI warning us about access from unsupported regions. It was cryptic and confusing.

We suspect it has to do with Edge function being used on Vercel which in turn uses Cloudflare. Thus, Vercel and cloudflare customers might be affected.

Comment · 2 years ago
Yeah great point, I will simplify the pricing and just say "Listen up to 10hrs of audio" instead.

It is a lot more clear and avoids any misunderstandings. Just need to make the changes to the app to do that.

Thanks for the great feedback

Comment · 2 years ago
Thanks so much yeah a few people asked for an API to make it easy too. Added it to my list of TODOs :)
Comment · 2 years ago
Totally fair, and I was really excited about the iOS safari built-in version. It didn't work for the book I bought and then after using AI bases TSS, I just couldn't go back.

I would love to be able to run the models on the device, and it will come in the future. The OSS models are not quite there from a quality standpoint yet. But they will surly get there

Comment · 2 years ago
Thanks a lot Nayam :). Let me know how it goes when you get a chance to try it, added chatbox to make it easier to leave feedback now

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton