Very cool! I'm working on something similar but am taking it much slower with a focus on accuracy. Mine recompiles into Golang to take advantage of built-in SIMD support.
I've been building the tooling around the PS2 binaries and hope to have a standalone PSS player out soon that can play PSS files as they are encoded, via simulated renderer, and via in-game engine renderer. The future is so bright with LLMs!
Not this exactly, but how your repository can be your swarm, and essentially be your harness.
Using Gitea/GitHub Actions within your repo and agent runner containers allow you to have agents working in your repos 24/7. Not just that, but in a containerized world you can just link up their brains over some shared storage. Using Antigravity, this means you can share the `brain` and its conversation directory with your agent runners and they can get the entire history of everything.
While building it out it becomes apparent that we are just getting started!
I just submitted it last night on HN, actually. So it should be on my profile in my submissions. It's written more about my experience rather than as a tutorial, but I think it becomes clear how it should work.
I enjoyed it, thank you for sharing and double thanks to Bluestein for surfacing it. Your point about declarative languages is interesting and mirrors my thoughts. Prompting is declarative even.
> Instruction latency analysis usually focuses on performance optimization—making code run as fast as possible. The Assembly Hall of Shame takes the opposite approach: searching for the absolute floor of single-instruction performance.
Mooltipass: https://www.themooltipass.com/
OnlyKey: https://onlykey.io/
reply