[dead]
How Claude Code works in large codebases
111–120 of 191 posts
Re: How Claude Code works in large codebases
#112Re: How Claude Code works in large codebases
#113Earlier quoted context omitted.
I have personally seen AI bypass this multiple times.
Sounds like they're still giving the model the keys to the kingdom, which is my point, stop giving the model the avenue to do catastrophic mistakes, it makes no sense.
If you’re message is in response to me, which I think it is, I deliberately don’t give access to credentials and env variables. I’ve worked to create restrictions and seen AI models use very interesting methods to bypass them.
Even now my prompt says the AI must verify the path of the files it intends to edit, and get permission before editing one file at a time and only after permission. I stop it from ignoring those rules once a day at least.
Re: How Claude Code works in large codebases
#114Just an anecdote: I was designing a project for LLMs onboarding and orchestration. Claude chose to read only the first 40 lines of each file. Later, in another session, looking for causes of low quality result, Claude detected the fault and changed the code to perform an AST analysis, so now the analyzer takes documentation lines and functions signature (input/output) as input. Claude's initial approach was really po…
I think it's taught to look at source code through a peephole for the sake of context preservation, but I feel like this could be a good use-case for some sub-logic or even a full sub-agent. Like, here sub-agent, you skim that file and tell me a summary, and highlight any areas related to X and Y so that I can look at them in my main context. You can also periodically observe the main work stream and interrupt me if…
I think what you suggest is like a local second order approximation, that can help. But, I think that the real problem is a global one, is about architectural taste, how the many local pieces interact and their friction. Currently that demands human expertize.
Re: How Claude Code works in large codebases
#115I don't have any LSP's hooked up to CC yet (going to fix that today), or particularly sophisticated CLAUDE.md files. So, if I've read this post correctly, that means that CC is navigating my codebase today by sending lots of it up to a model, and building an understanding. Is that correct? Did I misunderstand it? I kinda suspected there was more local inference going on somehow -- partly because the iteration times a…
I think that's correct. Which is kinda funny, I remember 10y ago that I was heavily relying on IntelliJ features to understand new codebases (jump to definition, find all usages of a function, navigate from SQL to the table in database tab etc.). It turns out, that for a machine, find and grep is all that's required.
Agents use find+grep because it's available everywhere and without any configuration, but they would still be more efficient with LSP. Once LSPs will be more easily configurable for agents, they will use them.
Re: How Claude Code works in large codebases
#116Earlier quoted context omitted.
I would never have these privileges granted directly to my account. Indeed it’s a good practice to use roles where supported (AWS has them) and explicitly switch when needed
The problem with agents is they regularly sidestep the guardrails and do what they want with a script anyway. The number of times I’ve seen Claude try to escape the folder it’s working in, and then for it to write a python script that does exactly what I told it it’s not allowed do supports that. If you use SSO and have an AWS config that Claude is allowed to see to get the correct role in the first place, it will ju…
And this is why it is the height of irresponsibility to run LLMs on your system. We know they are unreliable and just make things up; it's extremely foolish to go "yeah I'm going to let that run commands".
Re: How Claude Code works in large codebases
#117> Claude Code navigates a codebase the way a software engineer would: it traverses the file system, reads files, uses grep to find exactly what it needs, and follows references across the codebase. It operates locally on the developer’s machine and doesn’t require a codebase index to be built, maintained, or uploaded to a server.... > Agentic search avoids those failure modes. There's no embedding pipeline or central…
[dead]
Re: How Claude Code works in large codebases
#118I use Claude Code quite a bit and quite enjoy it, so I'm a bit confused by how often it's mentioned that you should have CLAUDE.md.
I mean: If there was something you could add to the prompt to consistently increase performance why isn't it in the system prompt already?
If it's all about clarifying a couple of local idiosyncrasies, shouldn't it be able to quickly get them by looking through the repo?
Does anyone have an example of a CLAUDE.md that really makes a difference for them?
In general, this article would really have profited massively from examples of good applications of those patterns.
Re: How Claude Code works in large codebases
#119Why can't Claude Code generate effective harness for us by inspecting the code base? I tried defining CLAUDE.md (or AGENTS.md), skills, plugins, but I'm not getting the effectiveness others claim to be. LSP plugin for example, CC doesn't to use LSP's symbol renaming and edits file one by one slowly, or it does not invoke the skill when I explicitly ask to remember to invoke when prompt contains a specific clue. Am I…
[flagged]
Re: How Claude Code works in large codebases
#120I use Claude Code quite a bit and quite enjoy it, so I'm a bit confused by how often it's mentioned that you should have CLAUDE.md. I mean: If there was something you could add to the prompt to consistently increase performance why isn't it in the system prompt already? If it's all about clarifying a couple of local idiosyncrasies, shouldn't it be able to quickly get them by looking through the repo? Does anyone have…
>I mean: If there was something you could add to the prompt to consistently increase performance why isn't it in the system prompt already?
I think about this a lot. So far I think we are mostly just being gaslit. That we can influence the AI to be better with a few encouraging words and role playing, actually seems absurd. Maybe there is some element of randomness introduced there or something. All these extra MD files don't seem to do nearly as much for results as people believe they do.