I've codified mine into a reusable workflow https://github.com/nothingnesses/agent-scaffold . To be honest, this isn't fool-proof though, since the agents can simply choose to ignore them, so I also like to pair this with deterministic linting and compile time checking.
For a Rust project, I created macros that output compiler errors when documentation and tests are not in a shape I want them to be, like missing function invocations or assertions, which forces the agent to address them, where otherwise they would've just worked around them by adding stupid trivial assertions like `assert_eq!(true, true)`.
That still isn't fool-proof either, but it helps minimise those instances. I'm bullish on the idea of integrating formal methods and model-checking with AI. I think that combo feels like a promising avenue for constraining the stochastic side of AI-generated code with something closer to deterministic verification. Provided you can write correct specs of course!
I've contributed to https://github.com/0xferrous/agent-box which allows you to bind-mount git repositories into containers that agents operate in, preventing the agents from accessing files that aren't bind-mounted. Your usual .gitignore can then be used to also ignore files within the repo to be bind-mounted, which prevents agents from accessing them at all, essentially working as a sandbox.
I also maintain https://github.com/nothingnesses/agent-images which allows you to use Nix to reproducibly spin up OCI container images containing agents and any other tools you need for development and use these with agent-box.
I use both at the moment to work on some personal projects with agents, where I set up multiple separate git worktrees for the agents to work in, preventing them from accessing anything outside of the worktrees and from trampling over each other's work.
I've contributed to https://github.com/0xferrous/agent-box which allows you to bind-mount git repositories into containers that agents operate in, preventing the agents from accessing files that aren't bind-mounted. Your usual .gitignore can then be used to also ignore files within the repo to be bind-mounted, which prevents agents from accessing them at all, essentially working as a sandbox.
I also maintain https://github.com/nothingnesses/agent-images which allows you to use Nix to reproducibly spin up OCI containers containing agents and any other tools you need and use these with agent-box.
I use both at the moment to work on some personal projects with agents, where I set up multiple separate git worktrees for the agents to work in, preventing them from accessing anything outside of the worktrees and from trampling over each other's work.
Out of curiosity, what do you think is wrong with monomorphization-based polymorphism? The other alternatives I'm aware of are 1. type-erasure via v-table based dynamic dispatch (which Rust also has in the form of the `dyn` keyword), which has performance and memory-allocation overhead and 2. macros, which Rust also has and, if used for polymorphism, would essentially be like compile-time monomorphization, but clunkier.
Maybe I'm missing something though and there are other alternatives done differently in other languages?
How does this compare to https://academy.fpblock.com/blog/quickcheck-hedgehog-validit... ? As far as I understand, Validity also has free generators and shrinking for types by having them implement various typeclasses that represent invariants and also has pre-made combinators to test properties with.
I know I'll sound like a rube but somehow it rubs me the wrong way that the rich and powerful are spending billions trying to establish multiplanetary civilisations despite the fact that we still have plenty of unfixed problems here at home that also deserve attention and resources, if not more so.
Still somewhat janky. I use it on my work machine (since it at least seems a bit faster than using VirtualBox) and regularly run into issues where npm won't build my project due to the existence of symlinks [1,2]. wslg windows also don't yet have first-party support from the windowing system [3]. I also remember having trouble setting up self-signed certs and getting SSL working.
> Standard protocols now exist for just about everything anyone needs.
I have been OOTL with the Wayland ecosystem for a few years. Does it provide a way for users to create and use input macros (similar to Autohotkey and xdotool) yet? That (in addition to remote desktop and screen casting) was one of the main blockers for me in daily-driving it.
For a Rust project, I created macros that output compiler errors when documentation and tests are not in a shape I want them to be, like missing function invocations or assertions, which forces the agent to address them, where otherwise they would've just worked around them by adding stupid trivial assertions like `assert_eq!(true, true)`.
That still isn't fool-proof either, but it helps minimise those instances. I'm bullish on the idea of integrating formal methods and model-checking with AI. I think that combo feels like a promising avenue for constraining the stochastic side of AI-generated code with something closer to deterministic verification. Provided you can write correct specs of course!