Ask HN: What are tools you have made for yourself since the advent of AI?

Here's what I did, roughly, YMMV. I have a lot of experience in managing scale and web platforms as it's what I did for like a decade so, grain of salt and all. Let's assume you have access to N number of linux machines with GPU's, for the sake of argument.

I have a small RPI acting as my homelab pihole and dns so what better than to run the management UI on?! So I wrote a small bun management plane, nothing fancy, just a react app with user auth + openidconnect for those that like that stuff. From there, you have compute pool (empty at the moment because it requires a deployed agent). I added the ability to directly ssh into a machine, install the "agent" with privilege so it can manage docker, and the agent talks back to the management plane over websockets. A keep alive / health / status / resource packet every 15 seconds. Streams if you are looking at logs or accessing a container. I used Codex for most of this work but defined the protocol and everything upfront using protobuf (even though it's websockets). It helped with the "vision" and keeping the agent like Codex on the rails through completion.

Once you have a pool (agents installed on your N number of linux machines), you can deploy apps (which are my way of saying, a container with a namespace) or you can deploy agents (which is my agent, custom made for this) that are assigned to a project. I decided Org structures are a great way to delegate workloads so that's how they are modeled. Projects provide the git repo, the docker registry for images and storage of artifacts, as well as the history of all the prompts the agents have done in the project. Useful if you want to go back and search through |thinking| tags to figure out the reasoning behind a decision.

All of this was built in like maybe a month with Codex initially, until my agent was up to the task of coding w/ an endpoint configured (OpenAI API initially, now, NVidia DGX Sparks). What really works well is the delegation. The agent's have a webui that is exposed via the project urls so you can interact with the "scrum masters" of each project. They also share a stream if they are on the same project (but different subprojects).

I too wish there was more information on this but I didn't keep the lack of it from stopping me experimenting and finding what works. I came from the Mesos/DCOS era where you stop thinking about the metal and think in pools of resources. It's a distributed systems problem.

Here’s the more detailed writeup: https://gist.github.com/adromero/e6a776e6a6100d53116f4053677...

I made a quick web app that lets me easily perform Bayesian evidence updates for a set of competing hypotheses. You drop your hypotheses into rows. Then for each piece of evidence, you add a column and fill its values with the odds of observing the evidence given that the corresponding hypotheses are true. The app then computes the posterior odds on the competing hypotheses, given the complete set of evidence. You can also import/export your results as CSV data.

1. A personal dashboard that is gloriously incongruent, but solves almost every problem where I have to glance at my phone: my home and car battery charge levels, my failing github actions, planes overflying my house, medication tracking, Life360 integration so I can ensure my kids charge their phones, sports and finance tickers, birthdays, fuel prices, public transport, integration with my bathroom scale....the list goes on and on. It has ticker mode, card mode and alert mode and lets me add features via a Github and Claude API integration.

2. A shopping list app that allows me and my partner to coordinate on our shopping

3. A recipes app that includes AI scanning

4. A standalone home battery dashboard/app

5. A fuel prices app that is tailored for the closest fuel stations and is ad-free

6. A tool to draw classroom supervision maps for my partner (thrown away already, I didn't want adware/bloatware so I built it, she used it, then I threw it away)

7. A quiz website, cos the one I used to play on was overrun by ads.

8. A time tracker that I'll throw away at the end of the tax year

And more, and that's just what I did for making my life easier, there are other more "enterprisey" things I am working on. They're web apps that I add to my iphone desktop or run on otherwise junky old tablets or on TVs.

The point is that they do exactly what I want them to do instead of relying on downloaded apps that get me 80-90% of the way there, even if they'd be classified as "AI slop". I know enough about security and caching that they aren't full of holes and don't kill upstream, but I don't really care about the code, and it's literally easier for me to build something new than to go to Google or an app store to find software that's full of ads.