"Quant Competitions Achievement

In 2024, I achieved 7th place at Quantiacs, a global quantitative trading competition. With a background in financial software, I built AIvestor to democratize AI-powered investing tools that were previously only available to institutions."

I have no idea of the legitimacy of Quantiacs, but for someone with these claims what they are selling is extremely unfaithful. Anyone with a sufficient knowledge of markets would understand the issues with what is being presented on the "portfolio" page, and the approach is bunk.

It appears that the product is based on some vibe-coded slop (https://github.com/LaurentiuGabriel/gpt-trading-agent). I personally would feel bad even thinking about trying to sell something like this to people.

And then I begin to think to myself that I should just read a book on the topic written by a trusted source who put a lot of effort into teaching the topic properly and presenting the information in a thoughtful way. So, I am back to books and mostly try to use LLMs to clarify certain questions or ideas I have.

1. It satisfies you curiosity (and curiosity is always valuable)

2. You can better utilize the LLM to expedite something you now have knowledge about

3. You still improve as an engineer/programmer/prompter/whatever

I still think it's very important not to outsource everything to AI because there is a lot of value in learning and doing things yourself which is an important part of life.

Also, in this model Cloudflare basically becomes the centralized gate keeper of you getting paid. And to me, this kind of sucks. It's not a very productive line of thought on my end -- I could see something like this happening as the internet trends toward centralization over time -- but it just feels bad.

It's called Vocast: https://github.com/cnrmurphy/vocast

Thinking about adding some things like queuing RSS feed items to be converted to audio and a feature for being able to do the conversion from my phone.

I wanted a way to listen to articles in my reading queue while out for a walk or just generally away from the computer. There are apps that can do this already, but I didn't want to pay for one and I thought it seemed simple enough to build myself. So, I built Vocast - a cli tool using local TTS to convert articles to audio and expose them as a podcast RSS feed. You can subscribe using your existing podcast app (Apple Podcasts has worked well for me).

Currently it uses Kokoro for TTS which I chose because it seems to be a good compromise between quality and speed. Generated audio files are stored in a local library and the cli provides commands to add, list, and delete those files. I use Tailscale to expose the local web server to my mobile device. I've provided instructions on how to do so in the README.

So far it's worked well for turning articles into something I can listen to while away from the desk so I'm pretty happy with the result. There are still cases where article formatting or writing style can produce awkward pacing, but for most articles the results are pretty good. If this is something that you need, I hope it serves you well too! I'd be interested to hear how others handle read-later content, whether there are features you'd want from a tool like this, or just your overall experience using it if you give it a try.

Comments URL: https://news.ycombinator.com/item?id=48479965

Points: 2

# Comments: 0