I solve problems. I automate things.
The main problem I see with this is that it's too much data for the agent to hold on to.
I experimented with a similar git storage approach, but instead each piece of data is weighted based on importance and gets promoted or demoted in a queue.
The most important data gets surfaced every single time the agent replies, so it never leaves the context window.
The last time I built a PC was almost 25 years ago. The gaming card seemed expensive at the time at $250.
I don't understand what's happened to PC building since. It's like it's a sport now or something. What's with the RGB crap? I remember wanting my PC to be quiet and out of sight. The screen and speakers were what mattered.
Now everyone's wearing crappy headphones. Everything is about how it looks. :/
Meta seem fairly innovative. Their r&d labs seem to produce some really cool things.
The basic issue is none of it seems to be making any money when it ends up in products and services.
Main reason there seems to be that their walled garden approach is tolerated at best. They just aren't very good at it outside of a feed.
I've been working on an RSS web app that solves this issue. Works offline, syncs across devices.
It works but trying to make something that scales to a lot of users is technically really hard.
Initially it was client only, but you can't really do that with rss due to cors issues. You have to proxy the feed downloads..
Anyway, I have a working prototype I'm just trying to fix bugs now so I can start showing it to people. Taken me a year almost to get this far
This project is an enhanced reader for Ycombinator Hacker News: https://news.ycombinator.com/.
The interface also allow to comment, post and interact with the original HN platform. Credentials are stored locally and are never sent to any server, you can check the source code here: https://github.com/GabrielePicco/hacker-news-rich.
For suggestions and features requests you can write me here: gabrielepicco.github.io