The highest quality codebase

Claude is really good at specific analysis, but really terrible at open-ended problems.

"Hey claude, I get this error message: <X>", and it'll often find the root cause quicker than I could.

"Hey claude, anything I could do to improve Y?", and it'll struggle beyond the basics that a linter might suggest.

It suggested enthusiastically a library for <work domain> and it was all "Recommended" about it, but when I pointed out that the library had been considered and rejected because <issue>, it understood and wrote up why that library suffered from that issue and why it was therefore unsuitable.

There's a significant blind-spot in current LLMs related to blue-sky thinking and creative problem solving. It can do structured problems very well, and it can transform unstructured data very well, but it can't deal with unstructured problems very well.

That may well change, so I don't want to embed that thought too deeply into my own priors, because the LLM space seems to evolve rapidly. I wouldn't want to find myself blind to the progress because I write it off from a class of problems.

But right now, the best way to help an LLM is have a deep understanding of the problem domain yourself, and just leverage it to do the grunt-work that you'd find boring.

That's why you treat it like a junior dev. You do the fun stuff of supervising the product, overseeing design and implementation, breaking up the work, and reviewing the outputs. It does the boring stuff of actually writing the code.

I am phenomenally productive this way, I am happier at my job, and its quality of work is extremely high as long as I occasionally have it stop and self-review it's progress against the style principles articulated in its AGENTS.md file. (As it tends to forget a lot of rules like DRY)

> That's why you treat it like a junior dev. You do the fun stuff of supervising the product, overseeing design and implementation, breaking up the work, and reviewing the outputs. It does the boring stuff of actually writing the code.

I am so tired of this analogy. Have the people who say this never worked with a junior dev before? If you treat your junior devs as brainless code monkeys who only exist to type out your brilliant senior developer designs and architectures instead of, you know, human beings capable of solving problems, 1) you're wasting your time, because a less experienced dev is still capable of solving problems independently, 2) the juniors working under you will hate it because they get no autonomy, and 3) the juniors working under you will stay junior because they have no opportunity to learn--which means you've failed at one of your most important tasks as a senior developer, which is mentorship.

I have mentored and worked with a junior dev. And the only way to get her to do anything useful and productive was to spell things out. Otherwise she got wrapped around the axle trying to figure out the complex things and was constantly asking for my help with basic design-level tasks. Doing the grunt work is how you learn the higher-level stuff.

When I was a junior, that's how it was for me. The senior gave me something that was structured and architected and asked me to handle smaller tasks that were beneath them.

Giving juniors full autonomy is a great way to end up with an unmaintainable mess that is a nightmare to work with without substancial refactoring. I know this because I have made a career out of fixing exactly this mistake.

I have never worked with junior devs as incompetent as you describe, having worked at AWS, Splunk/Cisco, among others. At AWS even interns essentially got assigned a full project for their term and were just told to go build it. Does your company just have an absurdly low hiring bar for juniors?

> Giving juniors full autonomy is a great way to end up with an unmaintainable mess that is a nightmare to work with without substancial refactoring.

Nobody is suggesting they get full autonomy to cowboy code and push unreviewed changes to prod. Everything they build should be getting reviewed by their peers and seniors. But they need opportunities to explore and make mistakes and get feedback.