Typst is amazing, but if you want HTML output, it's not quite there yet.

You don't need to subscribe to the NYT to play the games. There's a separate subscription.

I usually use Python or Rust for CLIs, but Optique makes me want to try out Typescript!

If you use a type checker in strict mode (e.g. pyright with "typeCheckingMode: strict") and a linter with strict rules (e.g. ruff with many rules enabled), the output space is constrained enough that you can get pretty consistent Python code. I'm not saying this is "good Python" overall, but it works pretty well with agents.

Who closes the gate? Is it Claude itself after it runs the verification? Who makes sure the verification did in fact run?

I usually have Claude confirm with me but I've seen it close it if its a unit test that passed for example.

You can't trust it 100%. Sometimes it will just refuse to fix a compiler or lint warning (often saying "This was a pre-existing issue...") or write a trivial test that does nothing and always passes.

> writes code with a lot of warnings > compacts > "This was a pre-existing issue..."

I still take this over writing code myself though.

I'm not saying you shouldn't. I'd say 70% of my work code is written by Claude Code or Codex. But this is something you should be aware of when interacting with agents.

Point being that there are multiple gates to one story, including human testing as one of them.

It is definitely worth a try. Just being able to squash changes to earlier commits without having to fiddle with fixups and interactive rebases is worth it for me. jj absorb is great too.

If you constantly switch between the two, you're going to have a hard time, but you can take a git repo, try jj for a while, and if you decide to go back, you don't lose anything.

Right, but that’s different from working in a team environment where everyone else continues using git.

No?

What problems, exactly, are you suggesting exist? I have used jj extensively on git teams and it has been seamless. The only people who have noticed or cared are the coworkers I’ve gotten to join me.

How so? I've used `jj` locally on teams where most (if not all) of the other team members were using git, and they only found out I was using `jj` when I told them.

You're confusing mixing git and jj in your local copy of the repo vs what it looks like to other people. You can use jj locally, and it interoperates perfectly with any git remote, and no one has to know you're even using it. From the point of view of other people, it doesn't matter.

I don't understand what you mean. The team I currently work with is 100% git while I only use jj anymore, and I've had zero issues?

fwiw I don't use it personally but some people on my team use it while the others use git, and nobody complains.

Yeah same here, have been using jj exclusively, the only reason people notice is because my branch names default to the changeid in my setup so I've had questions about the random looking strings.

You can use vi copy mode. It makes selection a lot easier.

Jujutsu does it, and it's quite nice.

A human has taste. They learn over time from codebase patterns and develop a sense of when an abstraction can be reused, improved or refactored. Agents often generate repeated code because the original file wasn't added to the context, and it's up to a human reviewer to recognise this.

In my experience, an agent will rarely recognise a common pattern and lift it into a new abstraction. It requires a human with taste and experience to do it. For example, an agent will happily add a big amount if branches in different places of the codebase where a strategy pattern or enum would be better (depending on the language).

If you have a working prompt or harness that ameliorates this, I'd be glad to see it.