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

111–120 of 630 posts

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

#111

Post by fragmede »

scuff3d wrote: post #106
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…

How anybody can read stuff like this and still take all this seriously is beyond me. This is becoming the engineering equivalent of astrology.

Feel free to run your own tests and see if the magic phrases do or do not influence the output. Have it make a Todo webapp with and without those phrases and see what happens!

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

#112

Post by xmcp123 »

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.

For awhile(maybe a year ago?) it seemed like verbal abuse was the best way to make Claude pay attention. In my head, it was impacting how important it deemed the instruction. And it definitely did seem that way.

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

#113

Post by fourthark »

reg_dunlop wrote: post #97
fourthark wrote: post #48

Earlier quoted context omitted.

This is exactly what the article is about. The tradeoff is that you have to throughly review the plans and iterate on them, which is tiring. But the LLM will write good code faster than you, if you tell it what good code is.

Exactly; the original commenter seems determined to write-off AI as "just not as good as me". The original article is, to me, seemingly not that novel. Not because it's a trite example, but because I've begun to experience massive gains from following the same basic premise as the article. And I can't believe there's others who aren't using like this. I iterate the plan until it's seemingly deterministic, then I stri…

Strongly agree about the deterministic part. Even more important than a good design, the plan must not show any doubt, whether it's in the form of open questions or weasel words. 95% of the time those vague words mean I didn't think something through, and it will do something hideous in order to make the plan work

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

#114

Post by winwang »

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…

Apparently LLM quality is sensitive to emotional stimuli?

"Large Language Models Understand and Can be Enhanced by Emotional Stimuli": https://arxiv.org/abs/2307.11760

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

#116

Post by red_hare »

ramoz wrote: post #79
red_hare wrote: post #74

I use Claude Code for lecture prep. I craft a detailed and ordered set of lecture notes in a Quarto file and then have a dedicated claude code skill for translating those notes into Slidev slides, in the style that I like. Once that's done, much like the author, I go through the slides and make commented annotations like "this should be broken into two slides" or "this should be a side-by-side" or "use your generate…

is your skill open source

Not yet... but also I'm not sure it makes a lot of sense to be open source. It's super specific to how I like to build slide decks and to my personal lecture style.

But it's not hard to build one. The key for me was describing, in great detail:

1. How I want it to read the source material (e.g., H1 means new section, H2 means at least one slide, a link to an example means I want code in the slide)

2. How to connect material to layouts (e.g., "comparison between two ideas should be a two-cols-title," "walkthrough of code should be two-cols with code on right," "learning objectives should be side-title align:left," "recall should be side-title align:right")

Then the workflow is:

1. Give all those details and have it do a first pass.

2. Give tons of feedback.

3. At the end of the session, ask it to "make a skill."

4. Manually edit the skill so that you're happy with the examples.

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

#117

Post by harrall »

jcdavis wrote: post #25
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…

Its a wild time to be in software development. Nobody(1) actually knows what causes LLMs to do certain things, we just pray the prompt moves the probabilities the right way enough such that it mostly does what we want. This used to be a field that prided itself on deterministic behavior and reproducibility. Now? We have AGENTS.md files that look like a parent talking to a child with all the bold all-caps, double emph…

It’s like playing a fretless instrument to me.

Practice playing songs by ear and after 2 weeks, my brain has developed an inference model of where my fingers should go to hit any given pitch.

Do I have any idea how my brain’s model works? No! But it tickles a different part of my brain and I like it.

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

#118

Post by bluegatty »

I don't see how this is 'radically different' given that Claude Code literally has a planning mode.

This is my workflow as well, with the big caveat that 80% of 'work' doesn't require substantive planning, we're making relatively straight forward changes.

Edit: there is nothing fundamentally different about 'annotating offline' in an MD vs in the CLI and iterating until the plan is clear. It's a UI choice.

Spec Driven Coding with AI is very well established, so working from a plan, or spec (they can be somewhat different) is not novel.

This is conventional CC use.

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

#119

Post by roncesvalles »

jamesmcq wrote: post #9

This all looks fine for someone who can't code, but for anyone with even a moderate amount of experience as a developer all this planning and checking and prompting and orchestrating is far more work than just writing the code yourself. There's no winner for "least amount of code written regardless of productivity outcomes.", except for maybe Anthropic's bank account.

Well it's less mental load. It's like Tesla's FSD. Am I a better driver than the FSD? For sure. But is it nice to just sit back and let it drive for a bit even if it's suboptimal and gets me there 10% slower, and maybe slightly pisses off the guy behind me? Yes, nice enough to shell out $99/mo. Code implementation takes a toll on you in the same way that driving does.

I think the method in TFA is overall less stressful for the dev. And you can always fix it up manually in the end; AI coding vs manual coding is not either-or.

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

#120

Post by dack »

bluegatty wrote: post #118

I don't see how this is 'radically different' given that Claude Code literally has a planning mode. This is my workflow as well, with the big caveat that 80% of 'work' doesn't require substantive planning, we're making relatively straight forward changes. Edit: there is nothing fundamentally different about 'annotating offline' in an MD vs in the CLI and iterating until the plan is clear. It's a UI choice. Spec Drive…

last i checked, you can't annotate inline with planning mode. you have to type a lot to explain precisely what needs to change, and then it re-presents you with a plan (which may or may not have changed something else).

i like the idea of having an actual document because you could actually compare the before and after versions if you wanted to confirm things changed as intended when you gave feedback

Post reply on HN