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

31–40 of 630 posts

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

#31

Post by streetfighter64 »

shepherdjerred wrote: post #19
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.

I really don't understand why there are so many comments like this. Yesterday I had Claude write an audit logging feature to track all changes made to entities in my app. Yeah you get this for free with many frameworks, but my company's custom setup doesn't have it. It took maybe 5-10 minutes of wall-time to come up with a good plan, and then ~20-30 min for Claude implement, test, etc. That would've taken me at least…

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?

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

#32

Post by wilkystyle »

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…

The author is referring to how the framing of your prompt informs the attention mechanism. You are essentially hinting to the attention mechanism that the function's implementation details have important context as well.

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

#33

Post by wilkystyle »

itypecode wrote: post #22
fragmede wrote: post #18

Earlier quoted context omitted.

Yeah, it's definitely a strange new world we're in, where I have to "trick" the computer into cooperating. The other day I told Claude "Yes you can", and it went off and did something it just said it couldn't do!

Solid dad move. XD

Is parenting making us better at prompt engineering, or is it the other way around?

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

#34

Post by shepherdjerred »

streetfighter64 wrote: post #31
shepherdjerred wrote: post #19

Earlier quoted context omitted.

I really don't understand why there are so many comments like this. Yesterday I had Claude write an audit logging feature to track all changes made to entities in my app. Yeah you get this for free with many frameworks, but my company's custom setup doesn't have it. It took maybe 5-10 minutes of wall-time to come up with a good plan, and then ~20-30 min for Claude implement, test, etc. That would've taken me at least…

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?

You're right, you're better than me!

You could've been curious and ask why it would take 1-2 days, and I would've happily told you.

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

#35

Post by MattGaiser »

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…

One of the well defined failure modes for AI agents/models is "laziness." Yes, models can be "lazy" and that is an actual term used when reviewing them.

I am not sure if we know why really, but they are that way and you need to explicitly prompt around it.

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

#36

Post by jamesmcq »

shepherdjerred wrote: post #19
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.

I really don't understand why there are so many comments like this. Yesterday I had Claude write an audit logging feature to track all changes made to entities in my app. Yeah you get this for free with many frameworks, but my company's custom setup doesn't have it. It took maybe 5-10 minutes of wall-time to come up with a good plan, and then ~20-30 min for Claude implement, test, etc. That would've taken me at least…

Trust me I'm very impressed at the progress AI has made, and maybe we'll get to the point where everything is 100% correct all the time and better than any human could write. I'm skeptical we can get there with the LLM approach though.

The problem is LLMs are great at simple implementation, even large amounts of simple implementation, but I've never seen it develop something more than trivial correctly. The larger problem is it's very often subtly but hugely wrong. It makes bad architecture decisions, it breaks things in pursuit of fixing or implementing other things. You can tell it has no concept of the "right" way to implement something. It very obviously lacks the "senior developer insight".

Maybe you can resolve some of these with large amounts of planning or specs, but that's the point of my original comment - at what point is it easier/faster/better to just write the code yourself? You don't get a prize for writing the least amount of code when you're just writing specs instead.

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

#38

Post by jamesmcq »

keyle wrote: post #29
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.

I partly agree with you. But once you have a codebase large enough, the changes become longer to even type in, once figured out. I find the best way to use agents (and I don't use claude) is to hash it out like I'm about to write these changes and I make my own mental notes, and get the agent to execute on it. Agents don't get tired, they don't start fat fingering stuff at 4pm, the quality doesn't suffer. And they ca…

I want to be clear, I'm not against any use of AI. It's hugely useful to save a couple of minutes of "write this specific function to do this specific thing that I could write and know exactly what it would look like". That's a great use, and I use it all the time! It's better autocomplete. Anything beyond that is pushing it - at the moment! We'll see, but spending all day writing specs and double-checking AI output is not more productive than just writing correct code yourself the first time, even if you're AI-autocompleting some of it.

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

#39

Post by nojito »

jamesmcq wrote: post #36
shepherdjerred wrote: post #19

Earlier quoted context omitted.

I really don't understand why there are so many comments like this. Yesterday I had Claude write an audit logging feature to track all changes made to entities in my app. Yeah you get this for free with many frameworks, but my company's custom setup doesn't have it. It took maybe 5-10 minutes of wall-time to come up with a good plan, and then ~20-30 min for Claude implement, test, etc. That would've taken me at least…

Trust me I'm very impressed at the progress AI has made, and maybe we'll get to the point where everything is 100% correct all the time and better than any human could write. I'm skeptical we can get there with the LLM approach though. The problem is LLMs are great at simple implementation, even large amounts of simple implementation, but I've never seen it develop something more than trivial correctly. The larger pr…

>I've never seen it develop something more than trivial correctly.

This is 100% incorrect, but the real issue is that the people who are using these llms for non-trivial work tend to be extremely secretive about it.

For example, I view my use of LLMs to be a competitive advantage and I will hold on to this for as long as possible.

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

#40

Post by ChadNauseam »

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…

The disconnect might be that there is a separation between "generating the final answer for the user" and "researching/thinking to get information needed for that answer". Saying "deeply" prompts it to read more of the file (as in, actually use the `read` tool to grab more parts of the file into context), and generate more "thinking" tokens (as in, tokens that are not shown to the user but that the model writes to refine its thoughts and improve the quality of its answer).
Post reply on HN