Comment by mattmanser | Hacker News Reader

Comment by mattmanser | Hacker News Reader

Parent Full thread

I was thinking about this last week.

I don't think this is necessarily a massive moat for senior programmers. I feel it's a not a massive jump to teach AI architecture patterns and good data modelling?

I feel that anthropic etc al. just haven't got to that training stage yet.

That then leaves you with the mental model problem. Yes, there then a large context problem, but again I was wondering if setting up an MCP that presented the AI a meaningful class map or something might help.

Essentially give the AI a mental model of the code. I personally find class maps useless as they tend to clash with my own mental model. But it might work with AI. The class map can obviously be built without AI, but then you might even get AI to go through the code function by function and annotate the class map with comments about any oddities of each function. The MCP server could even limit the size of the map, depending on what part of the code it's looking to change (working on the email sending, don't bother sending them the UI later).

I'm guessing someone's already tried it given some of the ridiculous .Claude folders I've seen[1] but I've seen no-one talking about whether it works or not yet in the discussions I follow.

[1] That I suspect are pointlessly over complicated and make CC worse not better

After having used Claude for a couple of months it's really nowhere close.

We are at the level of the original Waymo cars where they had to have a person behind the wheel ready to take the controls, just in case it inexplicably decided to drive off a bridge.

As Claude's safety driver I have to intervene in perhaps 25-50% of tasks. Some days I don't even open Claude because I'm working on a part of the codebase that has to be just so and I know Claude would mess it up.

The moat is real. I don't have any illusions that one day Claude will catch up but that's at least 5 years away.

Yeah, tried similar things.

The issue is that having them learn that on it's own is currently an inaccurate process with a lot of overlooking. I recently tried doing some of the techniques that fared well on smaller repositories on a giant monorepo, and while sometimes they did yield improvements, most often things got overlooked, dependencies forgot about, testing suites confused. And it wastes a ton of compute in the end for smaller yields.

It will get better, that I am sure of, but currently the best way is to introduce it an architecture, give it some samples so it can do what it does best - follow text patterns. But people are mostly trying to one-shot things with this magical AI they heard about without any proper investment of time and mindshare into it.

While some might say "oh that wont work well in legacy repositores, we got 6 architectures here", pointing that out and adding a markdown explaining each helps a ton. And not "hey claude generate me an architecture.md" but transferring the actual knowledge you have, together with all the thorny bits into documentation, which will both improve your AI usage and your organisation.

Reply on news.ycombinator.com