I have a hobby project on the side involving radio digital signal processing in Rust that I've been pure vibe coding, just out of curiosity to see how far I can get. On more than one occasion the hobby project has gotten bogged down in a bug that is immensely challenging to resolve. And since the project isn't in an area I have experience with, and since I don't have a solid "theory of the program", since it's a gray box because I've been vibe coding it, I've definitely seen CC get stuck and introduce regressions in tricky issues we previously worked through.
The use of Claude Code with my day job has been quite different. In my day job, I understand the code and review it carefully, and CC has been a big help.
I've had some success with a multi-threaded software defined radio (SDR) app in Rust that does signal processing. It's been useful for trying something out that's beyond my experience. Which isn't to say it's been easy. It's been a learning experience to figure out how to work around Claude's limitations.
I think there's plenty of scope for improvements like this. I haven't had the energy to pursue further improvements along these lines, but I suspect they could make it a better app.
My own purpose in using it is to be able to get back to any link that I've read or have potentially wanted to read at a later point in time. You scan see screenshots here: https://github.com/emwalker/digraph.
It's pretty manual at this point. The indexing is done by hand. The idea is kind of crazy, but I think it can be made to work, in the same way that Wikipedia is maintained by hand.
If you can crowdsource the indexing, you get yourself a manually curated search engine with a nice topic graph that can be traversed. A piece of this puzzle that hasn't been tackled yet is a reputation system to keep the signal-to-noise ratio high and deal with spam.
> What’s an example use case of where you use that system to find a link?
An example use case is that I come across some interesting long-form article on a topic I'm following, e.g., Shackleton's expedition, that's published on a nice website and that I don't have time to read. I can just drop the link in the right topic and get back to it without too much difficulty. Or that's the hope, anyway. (Doesn't always work out that like that.)
Another thing I'm interested in is what the topic structure ends up looking like as it's more fully fleshed out. So sometimes I'll drop in random links even if they're not that interesting, just to build out the topics.
I built a web app that keeps track of every link I ever find to be interesting. It allows for fine-grained topics (e.g., individual academic papers, or topics more specific than that). It groups the topics in a DAG, so that you can get to a topic via more than one path from the top. And it allows you to look at intersections of transitive closures over topics in order to narrow down a search.
It keeps a history of every change to the graph in Git, so one day you could potentially implement some form of time travel and see what the graph looked like at an earlier point in time without too much difficulty.
I have used the app every day for years. I feel like there's something promising there that is of general interest, but I have not figured out how to communicate the value.
It's definitely an arms race. Sort of like tax avoidance. As long as you have search engines ordering results, I guess you'll have people who seek to game the results. The question for me is whether what Google does can be improved upon. I think we can do much better.
This is the kind of recipe I see most often when searching for recipes. I wonder whether GP was a little lucky with his/her three links. (The lasagna recipe was an example of an SEO'd recipe.)
PG has recursive common table expressions, which allow you to traverse a tree or graph represented as an adjacency list in a single query. (No doubt there are other important things that graph DBs do.)
The use of Claude Code with my day job has been quite different. In my day job, I understand the code and review it carefully, and CC has been a big help.