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

241–250 of 630 posts

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

#241

Post by chaboud »

The author seems to think they've hit upon something revolutionary...

They've actually hit upon something that several of us have evolved to naturally.

LLM's are like unreliable interns with boundless energy. They make silly mistakes, wander into annoying structural traps, and have to be unwound if left to their own devices. It's like the genie that almost pathologically misinterprets your wishes.

So, how do you solve that? Exactly how an experienced lead or software manager does: you have systems write it down before executing, explain things back to you, and ground all of their thinking in the code and documentation, avoiding making assumptions about code after superficial review.

When it was early ChatGPT, this meant function-level thinking and clearly described jobs. When it was Cline it meant cline rules files that forced writing architecture.md files and vibe-code.log histories, demanding grounding in research and code reading.

Maybe nine months ago, another engineer said two things to me, less than a day apart:

- "I don't understand why your clinerules file is so large. You have the LLM jumping through so many hoops and doing so much extra work. It's crazy."

- The next morning: "It's basically like a lottery. I can't get the LLM to generate what I want reliably. I just have to settle for whatever it comes up with and then try again."

These systems have to deal with minimal context, ambiguous guidance, and extreme isolation. Operate with a little empathy for the energetic interns, and they'll uncork levels of output worth fighting for. We're Software Managers now. For some of us, that's working out great.

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

#242

Post by onion2k »

FuckButtons wrote: post #150
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…

That’s because it’s superstition. Unless someone can come up with some kind of rigorous statistics on what the effect of this kind of priming is it seems no better than claiming that sacrificing your first born will please the sun god into giving us a bountiful harvest next year. Sure, maybe this supposed deity really is this insecure and needs a jolly good pep talk every time he wakes up. or maybe you’re just suffer…

i suppose we will just have to write an English to pedantry compiler.

A common technique is to prompt in your chosen AI to write a longer prompt to get it to do what you want. It's used a lot in image generation. This is called 'prompt enhancing'.

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

#243

Post by therealdrag0 »

Bishonen88 wrote: post #224
mvkel wrote: post #218

> the workflow I’ve settled into is radically different from what most people do with AI coding tools This looks exactly like what anthropic recommends as the best practice for using Claude Code. Textbook. It also exposes a major downside of this approach: if you don't plan perfectly, you'll have to start over from scratch if anything goes wrong. I've found a much better approach in doing a design -> plan -> execute…

Dunno. My 80k+ LOC personal life planner, with a native android app, eink display view still one shots most features/bugs I encounter. I just open a new instance let it know what I want and 5min later it's done.

In 5 min you are one shotting smaller changes to the larger code base right? Not the entire 80k likes which was the other comments point afaict.

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

#244

Post by puchatek »

Bishonen88 wrote: post #240
vasco wrote: post #236

Earlier quoted context omitted.

What is a personal life planner?

Todos, habits, goals, calendar, meals, notes, bookmarks, shopping lists, finances. More or less that with Google cal integration, garmin Integration (Auto updates workout habits, weight goals) family sharing/gamification, daily/weekly reviews, ai summaries and more. All built by just prompting Claude for feature after feature, with me writing 0 lines.

Is it on GH?

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

#245

Post by guiambros »

scuff3d wrote: post #207
guiambros wrote: post #177

Earlier quoted context omitted.

If you read the transformer paper, or get any book on NLP, you will see that this is not magic incantation; it's purely the attention mechanism at work. Or you can just ask Gemini or Claude why these prompts work. But I get the impression from your comment that you have a fixed idea, and you're not really interested in understanding how or why it works. If you think like a hammer, everything will look like a nail.

I know why it works, to varying and unmeasurable degrees of success. Just like if I poke a bull with a sharp stick, I know it's gonna get it's attention. It might choose to run away from me in one of any number of directions, or it might decide to turn around and gore me to death. I can't answer that question with any certainty then you can. The system is inherently non-deterministic. Just because you can guide it a…

> The system is inherently non-deterministic.

The system isn't randomly non-deterministic; it is statistically probabilistic.

The next-token prediction and the attention mechanism is actually a rigorous deterministic mathematical process. The variation in output comes from how we sample from that curve, and the temperature used to calibrate the model. Because the underlying probabilities are mathematically calculated, the system's behavior remains highly predictable within statistical bounds.

Yes, it's a departure from the fully deterministic systems we're used to. But that's not different than the many real world systems: weather, biology, robotics, quantum mechanics. Even the computer you're reading this right now is full of probabilistic processes, abstracted away through sigmoid-like functions that push the extremes to 0s and 1s.

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

#246

Post by dakolli »

mvkel wrote: post #218

> the workflow I’ve settled into is radically different from what most people do with AI coding tools This looks exactly like what anthropic recommends as the best practice for using Claude Code. Textbook. It also exposes a major downside of this approach: if you don't plan perfectly, you'll have to start over from scratch if anything goes wrong. I've found a much better approach in doing a design -> plan -> execute…

wtf, why would you write 100k lines of plan to produce 30k loc.. JUST WRITE THE CODE!!!

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

#247

Post by dotancohen »

victorbjorklund wrote: post #153
xscott wrote: post #148

Earlier quoted context omitted.

Of course I can't be certain, but I think the "mixture of experts" design plays into it too. Metaphorically, there's a mid-level manager who looks at your prompt and tries to decide which experts it should be sent to. If he thinks you won't notice, he saves money by sending it to the undergraduate intern. Just a theory.

Notice that MOE isn’t different experts for different types of problems. It’s per token and not really connect to problem type. So if you send a python code then the first one in function can be one expert, second another expert and so on.

Can you back this up with documentation? I don't believe that this is the case.

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

#249

Post by YetAnotherNick »

I don't know. I tried various methods. And this one kind of doesn't work quite a bit of times. The problem is plan naturally always skips some important details, or assumes some library function, but is taken as instruction in the next section. And claude can't handle ambiguity if the instruction is very detailed(e.g. if plan asks to use a certain library even if it is a bad fit claude won't know that decision is flexible). If the instruction is less detailed, I saw claude is willing to try multiple things and if it keeps failing doesn't fear in reverting almost everything.

In my experience, the best scenario is that instruction and plan should be human written, and be detailed.

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

#250

Post by Bishonen88 »

dakolli wrote: post #246
mvkel wrote: post #218

> the workflow I’ve settled into is radically different from what most people do with AI coding tools This looks exactly like what anthropic recommends as the best practice for using Claude Code. Textbook. It also exposes a major downside of this approach: if you don't plan perfectly, you'll have to start over from scratch if anything goes wrong. I've found a much better approach in doing a design -> plan -> execute…

wtf, why would you write 100k lines of plan to produce 30k loc.. JUST WRITE THE CODE!!!

They didn't write 100k plan lines. The llm did (99.9% of it at least or more). Writing 30k by hand would take weeks if not months. Llms do it in an afternoon.
Post reply on HN