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

How I use Claude Code: Separation of planning and execution

boristane.com

Post reply on HN
Print view View original

191–200 of 630 posts

Re: How I use Claude Code: Separation of planning and execution

#191

Post by basch »

hashmap wrote: post #42
haolez wrote: post #12

> Notice the language: “deeply”, “in great details”, “intricacies”, “go through everything”. This isn’t fluff. Without these words, Claude will skim. It’ll read a file, see what a function does at the signature level, and move on. You need to signal that surface-level reading is not acceptable. This makes no sense to my intuition of how an LLM works. It's not that I don't believe this works, but my mental model doesn…

these sort-of-lies might help: think of the latent space inside the model like a topological map, and when you give it a prompt, you're dropping a ball at a certain point above the ground, and gravity pulls it along the surface until it settles. caveat though, thats nice per-token, but the signal gets messed up by picking a token from a distribution, so each token you're regenerating and re-distorting the signal. lea…

My mental model for them is plinko boards. Your prompt changes the spacing between the nails to increase the probability in certain directions as your chip falls down.

Re: How I use Claude Code: Separation of planning and execution

#193

Post by swe_dima »

Since everyone is showing their flow, here's mine:

* create a feature-name.md file in a gitignored folder

* start the file by giving the business context

* describe a high-level implementation and user flows

* describe database structure changes (I find it important not to leave it for interpretation)

* ask Claude to inspect the feature and review if for coherence, while answering its questions I ask to augment feature-name.md file with the answers

* enter Claude's plan mode and provide that feature-name.md file

* at this point it's detailed enough that rarely any corrections from me are needed

Re: How I use Claude Code: Separation of planning and execution

#194

Post by spagettnet »

manmal wrote: post #184
nostrademons wrote: post #85

Earlier quoted context omitted.

It's the attention mechanism at work, along with a fair bit of Internet one-up-manship. The LLM has ingested all of the text on the Internet, as well as Github code repositories, pull requests, StackOverflow posts, code reviews, mailing lists, etc. In a number of those content sources, there will be people saying "Actually, if you go into the details of..." or "If you look at the intricacies of the problem" or "If yo…

I don’t think this is a result of the base training data („the internet“). It’s a post training behavior, created during reinforcement learning. Codex has a totally different behavior in that regard. Codex reads per default a lot of potentially relevant files before it goes and writes files. Maybe you remember that, without reinforcement learning, the models of 2019 just completed the sentences you gave them. There w…

Modern LLM are certainly fine tuned on data that includes examples of tool use, mostly the tools built into their respective harnesses, but also external/mock tools so they dont overfit on only using the toolset they expect to see in their harnesses.

Re: How I use Claude Code: Separation of planning and execution

#195

Post by chickensong »

trueno wrote: post #77
chickensong wrote: post #55

Earlier quoted context omitted.

For Claude at least, the more recent guidance from Anthropic is to not yell at it. Just clear, calm, and concise instructions.

wait seriously? lmfao thats hilarious. i definitely treat claude like shit and ive noticed the falloff in results. if there's a source for that i'd love to read about it.

I don't have a source offhand, but I think it may have been part of the 4.5 release? Older models definitely needed caps and words like critical, important, never, etc... but Anthropic published something that said don't do that anymore.

Re: How I use Claude Code: Separation of planning and execution

#196

Post by Merad »

I've been working off and on on a vibe coded FP language and transpiler - mostly just to get more experience with Claude Code and see how it handles complex real world projects. I've settled on a very similar flow, though I use three documents: plan, context, task list. Multiple rounds of iteration when planning a feature. After completion, have a clean session do an audit to confirm that everything was implemented per the design. Then I have both Claude and CodeRabbit do code review passes before I finally do manual review. VERY heavy emphasis on tests, the project currently has 2x more test code than application code. So far it works surprisingly well. Example planning docs below -

https://github.com/mbcrawfo/vibefun/tree/main/.claude/archiv...

Re: How I use Claude Code: Separation of planning and execution

#198

Post by zahlman »

> After Claude writes the plan, I open it in my editor and add inline notes directly into the document. These notes correct assumptions, reject approaches, add constraints, or provide domain knowledge that Claude doesn’t have.

This is the part that seems most novel compared to what I've heard suggested before. And I have to admit I'm a bit skeptical. Would it not be better to modify what Claude has written directly, to make it correct, rather than adding the corrections as separate notes (and expecting future Claude to parse out which parts were past Claude and which parts were the operator, and handle the feedback graciously)?

At least, it seems like the intent is to do all of this in the same session, such that Claude has the context of the entire back-and-forth updating the plan. But that seems a bit unpleasant; I would think the file is there specifically to preserve context between sessions.

Post reply on HN