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

231–240 of 304 posts

Re: Writing a good Claude.md

#231

Post by tsimionescu »

stingraycharles wrote: post #162
llbeansandrice wrote: post #151

Earlier quoted context omitted.

If AI is supposed to deliver on this magical no-lift ease of use task flexibility that everyone likes to talk about I think it should be able to work with a README instead of clogging up ALL of my directories with yet another fucking config file. Also this isn’t portable to other potential AI tools. Do I need 3+ md files in every directory?

It’s not delivering on magical stuff. Getting real productivity improvements out of this requires engineering and planning and it needs to be approached as such. One of the big mistakes I think is that all these tools are over-promising on the “magic” part of it. It’s not. You need to really learn how to use all these tools effectively. This is not done in days or weeks even, it takes months in the same way becoming…

While I believe you're probably right that getting any productivity gains from these tools requires an investment, I think calling the process "engineering" is really stretching the meaning of the word. It's really closer to ritual magic than any solid engineering practices at this point. People have guesses and practices that may or may not actually work for them (since measuring productivity increases is difficult if not impossible), and they teach others their magic formulas for controlling the demon.

Re: Writing a good Claude.md

#232

Post by fpauser »

stingraycharles wrote: post #162
llbeansandrice wrote: post #151

Earlier quoted context omitted.

If AI is supposed to deliver on this magical no-lift ease of use task flexibility that everyone likes to talk about I think it should be able to work with a README instead of clogging up ALL of my directories with yet another fucking config file. Also this isn’t portable to other potential AI tools. Do I need 3+ md files in every directory?

It’s not delivering on magical stuff. Getting real productivity improvements out of this requires engineering and planning and it needs to be approached as such. One of the big mistakes I think is that all these tools are over-promising on the “magic” part of it. It’s not. You need to really learn how to use all these tools effectively. This is not done in days or weeks even, it takes months in the same way becoming…

>> [..] and it may not even be relevant anymore next year.

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Re: Writing a good Claude.md

#234

Post by grayhatter »

orbital-decay wrote: post #192
grayhatter wrote: post #134

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. 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…

This reads like you either have an idealized view of Real Engineering™, or used to work in a stable, extremely regulated area (e.g. civil engineering). I used to work in aerospace in the past, and we had a lot of silly Mr Tinkleberry canaries. We didn't strictly rely on them because our job was "extremely regulated" to put it mildly, but they did save us some time. There's a ton of pretty stable engineering subfields…

> There's no need to be upset with the fact that some people want to hack explosive stuff together before it becomes a predictable glacier of Real Engineering.

You misunderstand me. I'm not upset that people are playing with explosives. I'm upset that my industry is playing with explosives that all read, "front: face towards users"

And then, more upset that we're all seemingly ok with that.

The driving force of enshittifacation of everything, may be external, but degradation clearly comes from engineers first. These broader industry trends only convince me it's not likely to get better anytime soon, and I don't like how everything is user hostile.

Re: Writing a good Claude.md

#235

Post by swiftcoder »

mewpmewp2 wrote: post #194
llbeansandrice wrote: post #151

Earlier quoted context omitted.

If AI is supposed to deliver on this magical no-lift ease of use task flexibility that everyone likes to talk about I think it should be able to work with a README instead of clogging up ALL of my directories with yet another fucking config file. Also this isn’t portable to other potential AI tools. Do I need 3+ md files in every directory?

Is your logic that unless something is perfect it should not be used even though it is delivering massive productivity gains?

> it is delivering massive productivity gains

[citation needed]

Every article I can find about this is citing the valuation of the S&P500 as evidence of the productivity gains, and that feels very circular

Re: Writing a good Claude.md

#236

Post by gtaylor »

tsimionescu wrote: post #231
stingraycharles wrote: post #162

Earlier quoted context omitted.

It’s not delivering on magical stuff. Getting real productivity improvements out of this requires engineering and planning and it needs to be approached as such. One of the big mistakes I think is that all these tools are over-promising on the “magic” part of it. It’s not. You need to really learn how to use all these tools effectively. This is not done in days or weeks even, it takes months in the same way becoming…

While I believe you're probably right that getting any productivity gains from these tools requires an investment, I think calling the process "engineering" is really stretching the meaning of the word. It's really closer to ritual magic than any solid engineering practices at this point. People have guesses and practices that may or may not actually work for them (since measuring productivity increases is difficult…

Most countries don’t have a notion of a formally licensed software engineer, anyway. Arguing what is and is not engineering is not useful.

Re: Writing a good Claude.md

#237

Post by threecheese »

adastra22 wrote: post #141
jmathai wrote: post #121

Earlier quoted context omitted.

I have a /bootstrap command that I run which instructs Claude Code to read all system and project CLAUDE.md files, skills and commands. Helps me quickly whip it back in line.

Isn’t that what every new session does?

That also clears the context; a command would just append to the context.

Re: Writing a good Claude.md

#238

Post by nineteen999 »

stingraycharles wrote: post #162
llbeansandrice wrote: post #151

Earlier quoted context omitted.

If AI is supposed to deliver on this magical no-lift ease of use task flexibility that everyone likes to talk about I think it should be able to work with a README instead of clogging up ALL of my directories with yet another fucking config file. Also this isn’t portable to other potential AI tools. Do I need 3+ md files in every directory?

It’s not delivering on magical stuff. Getting real productivity improvements out of this requires engineering and planning and it needs to be approached as such. One of the big mistakes I think is that all these tools are over-promising on the “magic” part of it. It’s not. You need to really learn how to use all these tools effectively. This is not done in days or weeks even, it takes months in the same way becoming…

Learning how to equip a local LLM with tools it can use to interact with to extend its capabilities has been a lot of fun for me and is a great educational experience for anyone who is interested. Just another tool for the toolchest.

Re: Writing a good Claude.md

#240

Post by aqme28 »

nico wrote: post #82

> Claude often ignores CLAUDE.md > The more information you have in the file that's not universally applicable to the tasks you have it working on, the more likely it is that Claude will ignore your instructions in the file Claude.md files can get pretty long, and many times Claude Code just stops following a lot of the directions specified in the file A friend of mine tells Claude to always address him as “Mr Tinkle…

You could make a hook in Claude to re-inject claude.md. For example, make it say "Mr Tinkleberry" in every response, and failing to do so re-injects the instructions.
Post reply on HN