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

601–610 of 630 posts

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

#601

Post by LEDThereBeLight »

hbarka wrote: post #253
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…

>> Same reason that "Pretend you are an MIT professor" or "You are a leading Python expert" or similar works in prompts. This pretend-you-are-a-[persona] is cargo cult prompting at this point. The persona framing is just decoration. A brief purpose statement describing what the skill [skill.md] does is more honest and just as effective.

It’s not cargo culting, it does make a difference and there are papers on arxiv discussing it. The trouble is that it’s hard to tell whether it’ll help or hurt - telling it to act as an expert in one field may improve your result, or may make it lose some of the other perspectives it has which might be more important for solving the problem.

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

#603

Post by intellegix »

This separation of planning and execution is exactly the pattern I ended up building into an open source toolkit for Claude Code. The key insight that made autonomous loops work was giving the loop driver awareness of the CLAUDE.md file as the "plan" layer — the human edits CLAUDE.md between runs to steer the project, and the loop driver handles execution (session continuity, budget enforcement, stagnation detection, model fallback from Opus to Sonnet on consecutive timeouts).

The other piece that helped was a multi-model council system — before committing to a major architectural decision, the toolkit queries GPT-4, Claude, and Gemini simultaneously through Perplexity, then synthesizes with Opus. Having three models surface their assumptions (as the top comment here describes) catches more blind spots than any single model.

194 pytest tests, MIT licensed: https://github.com/intellegix/intellegix-code-agent-toolkit

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

#604

Post by winrid »

imiric wrote: post #378
winrid wrote: post #213

Earlier quoted context omitted.

But we can predict the outcomes, though. That's what we're saying, and it's true. Maybe not 100% of the time, but maybe it helps a significant amount of the time and that's what matters. Is it engineering? Maybe not. But neither is knowing how to talk to junior developers so they're productive and don't feel bad. The engineering is at other levels.

> But we can predict the outcomes [...] Maybe not 100% of the time So 60% of the time, it works every time. ... This fucking industry.

Again, it's called management. You're managing something unpredictable: the LLM.

This is nothing new, at all. Do you have a strategy that makes other engineers do what you want exactly 100% of the time?

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

#606

Post by basch »

hashmap wrote: post #293
basch wrote: post #191

Earlier quoted context omitted.

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.

i literally suggested this metaphor earlier yesterday to someone trying to get agents to do stuff they wanted, that they had to set up their guardrails in a way that you can let the agents do what they're good at, and you'll get better results because you're not sitting there looking at them. i think probably once you start seeing that the behavior falls right out of the geometry, you just start looking at stuff like…

Probably better could have described it as the distance between the pegs being the model weight, and the prompt defines the shape of the coin you’re dropping down.

I was half asleep when I wrote it the first time and knew it wasn’t what I wanted to say but couldn’t remember what analogy I was looking for.

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

#607

Post by streetfighter64 »

shepherdjerred wrote: post #62
jamesmcq wrote: post #47

Earlier quoted context omitted.

I'll bite, because it does seem like something that should be quick in a well-architected codebase. What was the situation? Was there something in this codebase that was especially suited to AI-development? Large amounts of duplication perhaps?

It's not particularly interesting. I wanted to add audit logging for all endpoints we call, all places we call the DB, etc. across areas I haven't touched before. It would have taken me a while to track down all of the touchpoints. Granted, I am not 100% certain that Claude didn't miss anything. I feel fairly confident that it is correct given that I had it research upfront, had multiple agents review, and it made th…

LOL, so why would I have asked you if the answer is self-admittedly not particularly interesting? It'd be like asking somebody why they took two days to put together an IKEA cupboard, of course the answer is uninteresting.

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

#608

Post by streetfighter64 »

fragmede wrote: post #59
streetfighter64 wrote: post #31

Earlier quoted context omitted.

I mean, all I can really say is... if writing some logging takes you one or two days, are you sure you _really_ know how to code?

We're not as good at coding as you , naturally.

You're being sarcastic, but clearly what you're saying is literally true. So...

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

#610

Post by 0x696C6961 »

le-mark wrote: post #498
0x696C6961 wrote: post #393

Earlier quoted context omitted.

This is exactly what I do. I assume most people avoid this approach due to cost.

Please explain what do you mean by “cost”?

You burn a lot of money on tokens for a solution that you throw away.
Post reply on HN