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

How I use every Claude Code feature

blog.sshh.io

Post reply on HN
Print view View original

161–170 of 193 posts

Re: How I use every Claude Code feature

#161

Post by brulard »

johnfn wrote: post #157

Does anyone else struggle with getting Claude to follow even the simplest commands in CLAUDE.md? I’ve completely give up on maintaining it because there’s a coin flip chance it disregards even the simplest instructions. For instance, (after becoming increasingly exasperated and whittling it down over and over), my CLAUDE file now has a single instruction, which says that any ai generated one-off script should be name…

I have quite long CLAUDE.md file and claude code follows it almost all the time. When it was ignoring some instructions, i told it to update CLAUDE.md to make sure it does. It emphasized it with uppercase and IMPORTANT! ALWAYS DO ... and that make it work for me like 95% of the time. And I do this for multiple project with different CLAUDE.mds with similar results. I don't know why your experience differs so much.

Re: How I use every Claude Code feature

#162

Post by distances »

riskable wrote: post #149
cheesedoodle wrote: post #137

What type of projects are you guys building? I bought Max and these features to try it out to build a more complex project (ROS2) and that does not seem to work out at all… HTML page, yes, embedded project not so much.

With all the LLM coding assistants, you have to get a feel for each model and which extension/interface you're using with them. Not only that, but it's also dependent on your project! For example, if you're writing a command line tool in Python, it doesn't really matter what model you use since they're all really great at Python (LOL). However, if you're writing a complicated SPA that uses say, Vue 3 with Vite (and s…

You do know that you can run Codex with the $20 ChatGPT subscription right? So the token waste doesn't matter that much. It's still slow though.

Re: How I use every Claude Code feature

#163

Post by ed_mercer »

swah wrote: post #91
ed_mercer wrote: post #70

Earlier quoted context omitted.

My m1 macbook pro works fine with +10 claude code sessions open at the same time (iTerm2). Are you using a terminal with a memory leak perhaps?

How are you managing 10 parallel agents??

sorry I'm not actively working on 10 at the time, but they are in memory and kept open for when I continue working on them. I'm only actively using 2 or 3 at the same time.

Re: How I use every Claude Code feature

#164

Post by krackers »

petesergeant wrote: post #26

> Generally my goal is to “shoot and forget”—to delegate, set the context, and let it work. Judging the tool by the final PR and not how it gets there. This feels like a false economy to me for real sized changes, but maybe I’m just a weak code reviewer. For code I really don’t care about, I’m happy to do this, but if I ever need to understand that code I have an uphill battle. OTOH reading intermediate diffs and tre…

No, I think it is normal. If it were easy to gain a mental model of the code simply by reading, then debugging would be trivial. The whole point of debugging is that there are differences between your mental model of the code and what the code is actually doing, that sometimes can't be uncovered unless you step through it line by line even if you're the one who wrote it.

It is why I am a bit puzzled by the people who use an LLM to generate code in anything other than a "tightly scoped" fashion (boilerplate, throwaway code, standalone script, single file, or at the function level). I'm not sure how that makes your job later on any easier if you have even a worse mental model of the code because you didn't even write it. And debugging is almost usually more tedious than writing code, so you've traded off the fun/easy part for a more difficult one. Seems like a faustian deal.

Re: How I use every Claude Code feature

#165

Post by riskable »

distances wrote: post #162
riskable wrote: post #149

Earlier quoted context omitted.

With all the LLM coding assistants, you have to get a feel for each model and which extension/interface you're using with them. Not only that, but it's also dependent on your project! For example, if you're writing a command line tool in Python, it doesn't really matter what model you use since they're all really great at Python (LOL). However, if you're writing a complicated SPA that uses say, Vue 3 with Vite (and s…

You do know that you can run Codex with the $20 ChatGPT subscription right? So the token waste doesn't matter that much. It's still slow though.

Tried that. I hit the limit way too fast. Faster than Claude Code, even!

GPT5-codex (medium) is such a token hog for some reason

Re: How I use every Claude Code feature

#166

Post by theshrike79 »

sshh12 wrote: post #50
nostrebored wrote: post #45

Earlier quoted context omitted.

Have you tried using light CLIs rather than MCP? I’ve found that CLIs are just easier for Claude, especially if you write them with Claude and during planning instruct it to think about adding guidance to users who get confused. Our auth, log diving, infra state, etc, is all usable via cli, and it feels pretty good when pointing Claude at it.

Yeah if that's possible or you are willing to build it, that's the right solution. Today pretty much all of my integrations are pure CLIs like that rather than MCPs. You can do anything you want via a CLI but MCP still exists as a standard that folks and platforms might want to adopt as a common interface.

MCPs still lack scoping in most cases.

It's not that practical to have an MCP that can connect to, for example, ALL of your corporate Google Drive. Not happening.

Why isn't it possible to limit it to a specific whitelisted set?

Re: How I use every Claude Code feature

#167

Post by theshrike79 »

cannonpalms wrote: post #154
mritchie712 wrote: post #102

> /clear + /catchup (Simple Restart): My default reboot. I /clear the state, then run a custom /catchup command to make Claude read all changed files in my git branch. I've found myself doing similar workarounds. I'm guessing anthropic will just make the /compact command do this instead soon enough.

I've found the latency of /compact makes it unusable. Perhaps this is just the result of my waiting until I have 0% context remaining. Fun fact, a large chunk of context is reserved for compaction. When you are shown that you have "0% context remaining," it's actually like 30% remaining that's reserved for compaction. And yet, for some reason I feel like 50% of the time, compaction fails because it runs out of contex…

The old rule of thumb is that when you compact, you've already lost.

Re: How I use every Claude Code feature

#168

Post by chickensong »

riskable wrote: post #151
risyachka wrote: post #80

Earlier quoted context omitted.

Whats interesting to see is not the project setup but the resulted generated code in a mid-sized project. To see if it is easy to digest, no repeated code etc or is it just slop that should be consumed by another agent and never by human.

I find the "slop" thing interesting because—to me—it looks like laziness. In the same way that anyone can tell ChatGPT to write something for them instead of writing it themselves and just having it check the work... Or going through multiple revisions before you're satisfied (with what it wrote). Code is no different! You can tell an AI model to write something for you and that's fine! Except you have to review it!…

It's always laziness. The people that do the bare minimum will likely continue to do so, regardless of AI.

I think we'll be dealing with slop issues for quite some time, but I also have hopes that AI will raise the bar of code in general.

Re: How I use every Claude Code feature

#169

Post by chickensong »

FooBarWidget wrote: post #53

Does anyone have any suggestions on making Claude prefer to use project internal abstractions and utility functions? My C++ project has a lot of them. If I just say something like "for I/O and networking code, check IOUtils.h for helpers" then it often doesn't do that. But mentioning all helper functions and classes in the context also seems like a bad idea. What's the best way? Are the new Skills a solution?

Skills seem like the way forward, but Claude still needs to be convinced to activate the skill. If that's not happening reliably, hooks should be able to help.

A sibling comment on hooks mentions some approaches. You could also try leveraging the UserPromptSubmit hook to do some prompt analysis and force relevant skill activation.

Re: How I use every Claude Code feature

#170

Post by brulard »

topherhunt wrote: post #155
simonw wrote: post #141

Earlier quoted context omitted.

I've sniffed Claude Code's HTTP traffic and confirmed that the CLAUDE.md file content (and AGENTS.md if it is @-referenced) is automatically included in the system prompt without it having to perform any additional file read operations.

Wow! That's.... discouraging, actually, considering how frequently Claude ignores my AGENTS.md guidance.

Did you notice the @-referencing requirement? AGENTS.md is not included by default, but CLAUDE.md should be
Post reply on HN