6 weeks of Claude Code • Hacker News Board

Re: 6 weeks of Claude Code

#601

Post by SV_BubbleTime » Wed, Aug 06, 2025, 2:18 AM UTC

bamboozled wrote: post #600

SV_BubbleTime wrote: post #555

Earlier quoted context omitted.

This isn’t a fair representation at all. I’ve been delighting all of my tedious tasks with as much context as I would give a person, and my personal win rate at this is substantially higher than I expected. If you give it trash and expect gold, sure, gambling.

Which is what I meant by, "you need to be very deliberate with it", you have to spend a lot of time on the inputs to get good outputs. Which makes it feel a fair bit less like "Intelligence" and a lot more like a calculator.

Context is everything. Whether they were talking to your junior employee, or to an LLM, if you don’t say what it is, you want don’t be surprised when it’s left to interpretation and comes out wrong.

Specifically, Claude coat is really good at making markdown files of plans and if you review them add in context, you can let it run a little more free than you would otherwise.

If you don’t feel like giving it, the right amount of context, make the job smaller, where there’s just less of it to begin with.

I wouldn’t tell my interns to change the formatting of these printf statements, because I don’t feel like it, but Claude does that stuff pretty great and doesn’t complain as much.

Re: 6 weeks of Claude Code

#602

Post by jerpint » Wed, Aug 06, 2025, 3:45 AM UTC

philipp-gayret wrote: post #572

jerpint wrote: post #538

Earlier quoted context omitted.

I wrote a tool for this, which allows you to co-create and maintain a context repository with your LLMs https://github.com/jerpint/context-llemur CLI for the humans, MCP for the LLMS. Whatever is in the context repository should be used by the LLM for its next steps and you are both responsible for maintaining it as tasks start getting done and the project evolves I’ve been having good success with it so far

I have a similar flow to this, but using files which are part of the repository. For you tool; What made you choose to version it with git but also write context is not code? Wouldn't you end up with multiple versions of say your backlog, and to what benefit?

The way I see it is that context evolves somewhat orthogonally to code. But you still want to track it in similar ways. Having git under the hood makes it easy to track its evolution and undo/diff things LLMs might decide to change, but also means that tracking your todos and new feature ideas don’t pollute your codebase

Re: 6 weeks of Claude Code

#603

Post by zed_the_face » Wed, Aug 06, 2025, 6:07 PM UTC

makingstuffs wrote: post #414

channel_t wrote: post #208

Earlier quoted context omitted.

Yes, can confirm that as a senior developer who has needed to spend huge amounts of time reviewing junior code from off-shore contractors with very detailed and explicit instructions, dabbling in agentic LLM coding tools like Claude Code has felt like like a gift from heaven. I also have concerns about said junior developers wielding such tools, because yes, without being able to supply the right kind of context and…

Ah mate I can’t relate more to the offshore component. I had a very sad experience where I recently had to let go of an offshore team due to them providing devs that essentially ‘junior with copilot’ but labelled as a ‘senior’. Time and time again I would find telltale signs of dumping LLM output into PRs n then claiming it as their own. Not a problem, but the code didn’t do what the detailed ticket asked and introdu…

Then why did you do it?