Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Writing a good Claude.md

humanlayer.dev

Post reply on HN
Print view View original

241–250 of 304 posts

Re: Writing a good Claude.md

#241

Post by aqme28 »

aiibe wrote: post #181

Writing and updating CLAUDE.md or AGENTS.md feels like pointless to me. Humans are the real audience for documentation. The code changes too fast, and LLMs are stateless anyway. What’s been working is just letting the LLM explore the relevant part of the code to acquire the context, defining the problem or feature, and asking for a couple of ways to tackle it. All in a one short prompt. That usually gets me solid opt…

This is true but sometimes your codebase has unique quirks that you get tired of repeating. "No, Claude, we do it this other way here. Every time."

Re: Writing a good Claude.md

#242

Post by nineteen999 »

grayhatter wrote: post #228
adastra22 wrote: post #158

Earlier quoted context omitted.

You don’t think people are trying very hard to understand LLMs? We recognize the value of interpretability. It is just not an easy task. It’s not the first time in human history that our ability to create things has exceeded our capacity to understand.

> You don’t think people are trying very hard to understand LLMs? We recognize the value of interpretability. It is just not an easy task. I think you're arguing against a tangential position to both me, and the person this directly replies to. It can be hard to use and understand something, but if you have a magic box that you can't tell if it's working. It doesn't belong anywhere near the systems that other humans…

> It doesn't belong anywhere near the systems that other humans use

Really for those of us who actually work in critical systems (emergency services in my case) - of course we're not going to start patching the core applications with vibe code.

But yeah, that frankenstein reporting script that half a dozen amateur hackers made a mess of over 20 years instead of refactoring and redesigning? That's prime fodder for this stuff. NOBODY wants to clean that stuff up by hand.

Re: Writing a good Claude.md

#243

Post by orbital-decay »

grayhatter wrote: post #229
orbital-decay wrote: post #221

Earlier quoted context omitted.

We're not going to advance the discussion this way. I also hate this kind of HN comment that makes grand sweeping statement like "LLMs are like having a fictional friend in a text file for the token predictor", because there's no way to tell whether you're just pulling these things out of your... to get internet points or actually have insightful parallels to make. Yes, during the Wright era aeronautics was absolutel…

> Yes, during the Wright era aeronautics was absolutely dominated by tinkering, before the aerodynamics was figured out. It wouldn't pass the high standard of Real Engineering. Remind me: did the Wright brothers start selling tickets to individuals telling them it was completely safe? Was step 2 of their research building a large passenger plane? I originally wanted to avoid that specific flight analogy, because it f…

As a matter of fact, commercial passenger service started almost immediately as the tech was out of the fiction phase. The airship were large, highly experimental, barely controllable, hydrogen-filled death traps that were marketed as luxurious and safe. First airliners also appeared with big engines and large planes (WWI disrupted this a bit). Nothing of that was built on solid grounds. The adoption was only constrained by the industrial capacity and cost. Most large aircraft were more or less experimental up until the 50's, and aviation in general was unreliable until about 80's.

I would say that right from the start everyone was pretty well aware about the unreliability of LLM-assisted coding and nobody was experimenting on unwitting people or forcing them to adopt it.

>Engineering at it's most basic is tricking physics into doing what you want.

Very well, then Mr Tinkleberry also passes the bar because it's exactly such a trick. That it irks you as a cheap hack that lacks rigor (which it does) is another matter.

Re: Writing a good Claude.md

#244

Post by beardedwizard »

solumunus wrote: post #216
whywhywhywhy wrote: post #179

Earlier quoted context omitted.

> Do I need 3+ md files in every directory? Don’t worry, as of about 6 weeks ago when they changed the system prompt Claude will make sure every folder has way more than 3 .md files seen as it often writes 2 or more per task so if you don’t clean them up…

Strange. I haven’t experienced this a single time and I use it almost all day everyday.

That is strange because it's been going on since sonnet 4.5 release.

Re: Writing a good Claude.md

#246

Post by solumunus »

grayhatter wrote: post #134
crystal_revenge wrote: post #122

Earlier quoted context omitted.

I suspect you’re misjudging the friend here. This sounds more like the famous “no brown m&ms” clause in the Van Halen performance contract. As ridiculous as the request is, it being followed provides strong evidence that the rest (and more meaningful) of the requests are. Sounds like the friend understands quite well how LLMs actually work and has found a clever way to be signaled when it’s starting to go off the rai…

> I suspect you’re misjudging the friend here. This sounds more like the famous “no brown m&ms” clause in the Van Halen performance contract. As ridiculous as the request is, it being followed provides strong evidence that the rest (and more meaningful) of the requests are. I'd argue, it's more like you've bought so much into the idea this is reasonable, that you're also willing to go through extreme lengths to recon…

I use agents almost all day and I do way more thinking than I used to, this is why I’m now more productive. There is little thinking required to produce output, typing requires very little thinking. The thinking is all in the planning… If the LLM output is bad in any given file I simply step in and modify it, and obviously this is much faster than typing every character.

I’m spending more time planning and my planning is more comprehensive than it used to be. I’m spending less time producing output, my output is more plentiful and of equal quality. No generated code goes into my commits without me reviewing it. Where exactly is the problem here?

Re: Writing a good Claude.md

#248

Post by aiibe »

aqme28 wrote: post #241
aiibe wrote: post #181

Writing and updating CLAUDE.md or AGENTS.md feels like pointless to me. Humans are the real audience for documentation. The code changes too fast, and LLMs are stateless anyway. What’s been working is just letting the LLM explore the relevant part of the code to acquire the context, defining the problem or feature, and asking for a couple of ways to tackle it. All in a one short prompt. That usually gets me solid opt…

This is true but sometimes your codebase has unique quirks that you get tired of repeating. "No, Claude, we do it this other way here. Every time."

Quirks are pretty much unavoidable. I tend to get better results using Codex. It sticks to established patterns. Slow, but more deliberate. Claude focuses more on speed.

Re: Writing a good Claude.md

#249

Post by adastra22 »

grayhatter wrote: post #228
adastra22 wrote: post #158

Earlier quoted context omitted.

You don’t think people are trying very hard to understand LLMs? We recognize the value of interpretability. It is just not an easy task. It’s not the first time in human history that our ability to create things has exceeded our capacity to understand.

> You don’t think people are trying very hard to understand LLMs? We recognize the value of interpretability. It is just not an easy task. I think you're arguing against a tangential position to both me, and the person this directly replies to. It can be hard to use and understand something, but if you have a magic box that you can't tell if it's working. It doesn't belong anywhere near the systems that other humans…

We used the steam engine for 100 years before we had a firm understanding of why it worked. We still don’t understand how ice skating works. We don’t have a physical understanding of semi-fluid flow in grain silos, but we’ve been using them since prehistory.

I could go on and on. The world around you is full of not well understood technology, as well as non deterministic processes. We know how to engineer around that.

Re: Writing a good Claude.md

#250

Post by adastra22 »

gyomu wrote: post #214
adastra22 wrote: post #158

Earlier quoted context omitted.

You don’t think people are trying very hard to understand LLMs? We recognize the value of interpretability. It is just not an easy task. It’s not the first time in human history that our ability to create things has exceeded our capacity to understand.

Your comment would be more useful if you could point us to some concrete tooling that’s been built out in the last ~3 years that LLM assisted coding has been around to improve interpretability.

That would be the exact opposite of my claim: it is a very hard problem.
Post reply on HN