I was always experimenting with different agents and models, and I wanted to track how much I use eg codex vs opencode vs hermes, and which models I use.
So I made, kind of last.fm/waka-code for agents where I track (anonymous) usage per project
Data is fully anonymous, all I collect is (agent, model, project name [can be mapped to something else to hide the true name]) and everything is opt-in by default (per project)
It’s not surprising that it inspires ire, even if that wasn’t my intent.
It’s a politically charged subject, and I’m taking a polarizing, US-centric, anti-regulatory position towards free speech, on top of my suggestion of using NATO funding as leverage to advance US speech policy.
Plus, a lot of people feel a great deal of partisan ill-will towards X and Elon Musk, irrespective of any of these issues.
Oh man I forgot to mention Quake, but yeah rocket jumping on Quake was maybe my first experience with awesome movement and I spent a lot of time perfecting rocket jumping in Q3DM6. Quake might have even been the first 3D game or atleast FPS ever to have that kind of fast & skillful movement?
LLM driven coding can yield awesome results, but you will be typing a lot and, as article states, requires already well structured codebase.
I recently started with fresh project, and until I got to the desired structure I only used AI to ask questions or suggestions. I organized and written most of the code.
Once it started to get into the shape that felt semi-permanent to me, I started a lot of queries like:
```
- Look at existing service X at folder services/x
- see how I deploy the service using k8s/services/x
- see how the docker file for service X looks like at services/x/Dockerfile
- now, I started service Y that does [this and that]
- create all that is needed for service Y to be skaffolded and deployed, follow the same pattern as service X
```
And it would go, read existing stuff for X, then generate all of the deployment/monitoring/readme/docker/k8s/helm/skaffold for Y
With zero to none mistakes.
Both claude and gemini are more than capable to do such task.
I had both of them generate 10-15 files with no errors, with code being able to be deployed right after (of course service will just answer and not do much more than that)
Then, I will take over again for a bit, do some business logic specific to Y, then again leverage AI to fill in missing bits, review, suggest stuff etc.
It might look slow, but it actually cuts most boring and most error prone steps when developing medium to large k8s backed project.
My workflow with a medium sized iOS codebase is a bit like that. By the time everything works and is up to my standards, I‘ve usually taken longer, or almost as long, as if I‘d written everything manually. That’s with Opus-only Claude Code. It’s complicated stuff (structured concurrency and lots of custom AsyncSequence operators) which maybe CC just isn‘t suitable for.
Whipping up greenfield projects is almost magical, of course. But that’s not most of my work.
One thing I’ve been looking for in an ID generator is a way to supply a blocklist. There are a number of character combinations I’d like to avoid in IDs, because they might be offensive or get stuck in filters when copy-pasted (e.g. in a URI).
This can be solved in user space by regenerating if the character sequences are detected, but this a) skews the distribution, and b) potentially takes time, especially when the ID generator is made to not be “too fast”. I want to generate a single ID that passes the blocklist in a timeframe that is not too fast, if that makes sense.
Is there an ID generator that takes this into consideration?
So I made, kind of last.fm/waka-code for agents where I track (anonymous) usage per project
here is the example of my profile: https://clankerlog.ai/kodisha
Data is fully anonymous, all I collect is (agent, model, project name [can be mapped to something else to hide the true name]) and everything is opt-in by default (per project)
reply