And by the fact of the longest part of programming being digesting code you didn’t write, in effect you’ve taken a long-cut and could have written it yourself faster.

The conclusion doesn’t follow from the premise. Just because an LLM may need to tweak something doesn’t mean it necessarily would have been faster to do it manually. Humans need to tweak things all the time, it’s called revising, and it’s an important part of improving code.

But I wouldn’t claim that using LLMs is always faster than coding manually, nor the opposite. There are times when LLMs do slow me down. It’s important to recognize when that risk is high.

But I’m quite certain that for prototyping specifically, i.e. building a desired UX to get a feel for it and experiment with whether the ideas are sound, LLMs are faster.

So you don’t get a valid answer, you just get a convincing one.

That’s why you shouldn’t trust an LLM’s reasoning; it doesn’t actually have sound reasoning abilities. You shouldn’t rely on an LLM to reason about problems, you should use it to generate code quickly when the reasoning has either already been done by a human and/or it exists in its training set. LLMs are closer to a search engine than a problem solver.

When asking the person why they did it…

I see no reason why this process is mutually exclusive with using an LLM. You can use both human reasoning and LLM code generation.

No disagreement from me about trivial changes. I make them in my editor all the time, assuming I even have an editor in front of me. Sometimes I don’t, and it’s possible to use dictation to an LLM to make trivial changes without touching a keyboard.

That means that reviews of LLM outputted code by their nature are either invalid and/or non-optimal.

Not convincing. I’ve given my reasons

Again, no one suggested that I would prototype with the LLM and then completely trust what it tells me about the code and what it learned from writing it. That is stupid.

You get the LLM to write code quickly and then you review it and perform experiments manually.

What you did not create, you have not understood.

So just because I didn’t write a book means I could never understand it from reading it? Are editors useless in the world of book publishing? Then what is the point of code review?

You act as if my LLM-assisted prototyping implies I made no decisions and didn’t read any code. That’s obviously a terrible way to use LLMs.

In the case of Rust, it makes sense both as a UX win and a way to abstract certain requirements of the build system. Languages don’t agree on how to do things like linking packages into a binary or versioning packages. If Rust left all of that unspecified, we’d probably have multiple competing package managers and ecosystems.

I thought Bazel was just a build system, not a package manager.

Not always. Prototyping can be valuable in many circumstances when you don’t know the shape you’d like the code to take. Sometimes you need to try something before you know if it’s right. I’d rather throw away prototype code written by an LLM than code I had to write the hard way.

I don’t think it’s very hard to understand. It reduces the up-front cost of development.

That is the point. By making smaller PRs, you inevitably end up with dependencies between them. So you’d like to stack them.

Yea if you don’t explicitly give it direction on how to keep the code maintainable, it will gladly just spew shit into the same file until you have 10K LOC in it.

No because your code is shit; you would be helping us reach singularity faster.

Such a good book. I still have no idea what it was about.

You don’t know the direct impact of this project on data center usage because you haven’t observed the development process. And you don’t know whether it infringes on copyright because you haven’t read the code.

How do you know it was built irresponsibly without reading the code, which is something you should be doing when adopting a dependency anyway?

If you identify with this post and you are in a manager position, please heed my warning. Throw away your prototypes. Stop vibing “quick fixes to unblock me”. Stop trying to help your devs because you think you’re superman now. You are only pissing everyone off, I promise. The devs who didn’t stop coding while you were off doing important manager/product stuff are the ones who understand what’s best for the codebase. And yes, they also know how to use LLMs.

Just because you feel like you have a new superpower doesn’t mean that everyone needs to be saved. Follow the damn engineering process.

I would say it’s more than just an icky feeling. It’s a justified moral opposition. But otherwise I agree. Just a tool.

And it was incredibly affordable compared to today.

OH! tmux obviously. It’s rock solid.

foot has been pretty solid for me. No complaints.

Tmux has better keybinding support in my experience. I started on tmux, tried zellij, but I wasn’t able to migrate my keybindings over. So I’m still with tmux.

Guys. This problem is solved already. Landlock, bubblewrap, UNIX DAC.