tsz

I love nextest. without it my CI could take hours https://github.com/tsz-org/tsz/actions/runs/29002057457/job/... watch it running 32.5k unit tests without breaking a sweat!

This is the right take. I wouldn't dare to write a TypeScript compiler a year ago but now I'm trying it and I have to say this has taught me so much about compilers, Rust and performance overall that wouldn't be possible before. It's a lot of fun to embrace the new technology and do bigger things. Doing this sort of project is giving me a glimpse of what it is going to be like managing software projects. As software engineers we have to learn how to manage much bigger changes and in a much higher level of abstraction. I personally don't think models are good enough for this level of automation yet but in a weekend that I had access to Fable I could see how things are going to change soon. Most of criticism towards LLM coding was not applicable to Fable. I'm not hyping anything, just an observation. The DJ analogy is useful actually. I liv

I'm making a TypeScript type checker in Rust. tsz is my main side project. Trying to learn from this for how to make software in fully automated fashion. tsz's goal is to match tsc (tsgo) but perform better. I am not passing all tsc's own test cases and working towards making it work on complex type packages. https://github.com/tsz-org/tsz

Shameless plug. I'm writing a TypeScript checker in Rust. It's not a port. I made this with a different architecture that hopefully once is done will be proven to be a better set of trade-off https://github.com/tsz-org/tsz

I have been using it for less than an hour so take this with a grain of salt of being excited for the new tech. In a project like mine (https://github.com/tsz-org/tsz) I am constantly frustrated that models were not doing enough research and were not taking into account other situations. Again and again models would produce code that would fix one thing and break 2 other tests that were "unrelated". With Fable it seems like tasks are taking much longer (I have not seen a pull request from Fable sessions yet) but reading the transcription of those sessions I can see how it is doing the right thing by not leaving any stone unturned. As the article says, it's hard to communicate this "feeling" about models because it is very project specific but I thought I share

I've been doing the same experiment in tsz[1] for a while now (the same past five months in fact) and I have come to very similar conclusions. Lots of harness to enforce good architecture splits. Lots of tests and CI. My point of working on tsz is to learn how to do very big projects with AI. Eventually the same workflows and attitude can be leveraged to build customer product apps with UI as well. I see that OpenAI is leveraging automated browser testing and even videos as part of their workflow. I think as models get better this direction for making software would eventually make sense. I don't think we're there yet though. But at least, unlike OpenAI vague claims I can share the output with you to see! Most of the solutions that offer a very high level of automation like Lovable are a bit too optimistic and solutions are not tightly co

In my project I let the agents communicate in GitHub issues and pull requests like humans do. I kinda stopped trying making orchestration frameworks. You can see the slop here https://github.com/mohsen1/tsz

> Honest status > Not at 100% - and I want to be straight about why that's a longer road... https://github.com/user-attachments/assets/961eff6c-0060-45d... I just want Claude Code to stop giving up on achieving tasks. It's so annoying. Even with `/goal` or the new `ultracode` it gives up constantly. My project is very complex (https://github.com/mohsen1/tsz) but Codex has no problem keep grinding without stopping like that

Now PRs are piling up! https://github.com/mohsen1/tsz/pulls

Lots and lots of guardrails to not allow slop. In tsz I have hard gates that disallow doing work in the wrong crate etc. https://github.com/mohsen1/tsz

Yes indeed. More than 1 million lines of code (including tests) is jumping lots of hoops but with LLMs it's not as painful so you can just ask it to do the hard things. Example of a Claude Code session after 2 hours of "Crunching" that came out without results https://github.com/mohsen1/tsz/pull/4868 (Edit I force pushed to PR to solve the problem, you can see the initial refuse message in the initial version of PR description) Funny thing is, the last percent of the test have been so hard to work on that Opus 4.7 routinely bails and says "it's too involved or complicated" so I had to add prompts specifically asking it not to bail.

I think the same issue from a couple of days ago is resurfaced because I can't see Pull Requests that were opened just minutes ago and merged PRs are still showing in the list: https://github.com/mohsen1/tsz/pulls