As you read, pages would be broken down and fed into this layer.

While reading, I needed something to do. I wanted to talk to the text, I wanted to leave notes, I wanted to use to use my keyboard to quickly flip through pages.

The only good available option on a Mac was "Preview" and it was ok, but definitely not there. So I built Quincy primarily for myself.

With it you can - "Talk" to the page you're reading, create a quiz about the page, and get a good summary - "Read" the page out-loud. Have your Mac read to you while you follow along. This helps with comprehension. - Copy text (to paste into an LLM), leave notes, bookmarks, etc.... - Anything else you'd want with a nice PDF reader

It's fully local. No cloud-sync (yet). All LLM calls are based on your keys. And TBH, you don't even need to use the AI features for this to be useful.

Try it out. Let me know what you guys think. This has been a quick project, so very rough around the edges. I plan on keeping it going (still haven't finished my book), and potentially open-sourcing down the line.

Comments URL: https://news.ycombinator.com/item?id=48429735

Points: 6

# Comments: 9

Comments URL: https://news.ycombinator.com/item?id=47655415

Points: 3

# Comments: 0

I realized that sometimes I'm pretty good at making random guesses about the future. (I.E, I think OpenAI will beat Anthropic in the short term, etc...)

However, I'm bad at converting these guesses into actual market plays I can profit from.

As such, I wanted to make a tool that connects to the right APIs and launches a swarm of agent experts to generate related plays based on your prediction.

The very first super shitty V0 MPV just has Polymarket/Kalshi bets, but I will be adding a more complex agentic harness, api sources for stocks/ETFs/options.

In the future, I'd imagine this can give you recs for all those, with some degree of certainty. Ideally, this allows lazy but intelligent retail investors to make money.

For now, the project is in open-source format; either run it yourself or send me an email at oleksandr.gorpynich@gmail.com if you'd be interested in using this commercially once I get further down the line.

Comments URL: https://news.ycombinator.com/item?id=47652476

Points: 3

# Comments: 0

To try the demo website (with the demo/mock data), checkout

https://odem-git-main-skymark.vercel.app/ Email: demo@gmail.com Pass: test123

It's super early stage, and mostly mock data, but it's been pretty useful so far. It's got - Historical price data for parts (predictions?) - Supply chain risk calculation (for those hoping to get past the prototype stage) - Alternative part finder (mock on demo) - LLM-based part search (mock on demo) - GIT-ish BOM management - CSV Import/Export - And more :)

To any hardware founders out there, are there any features you'd kill to have while working on your products?

Also, if anyone wants to try it out properly for their projects, let me know. Will not only let you use it for free, but also build out whatever you want.

Comments URL: https://news.ycombinator.com/item?id=47257960

Points: 1

# Comments: 0