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

171–180 of 630 posts

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

#171

Post by majormajor »

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…

> If it did work, well, the oldest trick in computer science is writing compilers, i suppose we will just have to write an English to pedantry compiler.

"Add tests to this function" for GPT-3.5-era models was much less effective than "you are a senior engineer. add tests for this function. as a good engineer, you should follow the patterns used in these other three function+test examples, using this framework and mocking lib." In today's tools, "add tests to this function" results in a bunch of initial steps to look in common places to see if that additional context already exists, and then pull it in based on what it finds. You can see it in the output the tools spit out while "thinking."

So I'm 90% sure this is already happening on some level.

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

#172

Post by apsurd »

epec254 wrote: post #160
wokwokwok wrote: post #151

This is the way. The practice is: - simple - effective - retains control and quality Certainly the “unsupervised agent” workflows are getting a lot of attention right now, but they require a specific set of circumstances to be effective: - clear validation loop (eg. Compile the kernel, here is gcc that does so correctly) - ai enabled tooling (mcp / cli tool that will lint, test and provide feedback immediately) - ove…

Huge +1. This loop consistently delivers great results for my vibe coding. The “easy” path of “short prompt declaring what I want” works OK for simple tasks but consistently breaks down for medium to high complexity tasks.

Can you help me understand the difference between "short prompt for what I want (next)" vs medium to high complexity tasks?

What i mean is, in practice, how does one even get to a a high complexity task? What does that look like? Because isn't it more common that one sees only so far ahead?

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

#174

Post by raw_anon_1111 »

ValentineC wrote: post #143
raw_anon_1111 wrote: post #75

Earlier quoted context omitted.

It isn’t slower. I use my personal ChatGPT subscriptions with Codex for almost everything at work and use my $800/month company Claude allowance only for the tricky stuff that Codex can’t figure out. It’s never application code. It’s usually some combination of app code + Docker + AWS issue with my underlying infrastructure - created with whatever IAC that I’m using for a client - Terraform/CloudFormation or the CDK.…

Curious: what are some cases where it'd make sense to not pay for the 20x plan (which is $200/month), and provide a whopping $800/month pay-per-token allowance instead?

Who knows? It’s part of an enterprise plan. I work for a consulting company. There are a number of fallbacks, the first fallback if we are working on an internal project is just to use our internal AWS account and use Claude code with the Anthropic hosted on Bedrock.

https://code.claude.com/docs/en/amazon-bedrock

The second fallback if it is for a customer project is to use their AWS account for development for them.

The rate my company charges for me - my level as an American based staff consultant (highest bill rate at the company) they are happy to let us use Claude Code using their AWS credentials. Besides, if we are using AWS Bedrock hosted Anthropic models, they know none of their secrets are going to Anthropic. They already have the required legal confidentiality/compliancd agreements with AWS.

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

#175

Post by raw_anon_1111 »

imron wrote: post #158
raw_anon_1111 wrote: post #107

Earlier quoted context omitted.

You’re assuming rational behavior from a company that doesn’t care about losing billions of dollar. Have you tried Codex with OpenAi’s latest models?

Not in the last 2 months. Current clause subscription is a sunk cost for the next month. Maybe I’ll try codex if Claude doesn’t lead anywhere.

I use both. As I’m working, I tell each of them to update a common document with the conversation. I don’t just tell Claude the what. I tell it the why and have it document it.

I can switch back and forth and use the MD file as shared context.

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

#177

Post by guiambros »

scuff3d wrote: post #146
fragmede wrote: post #111

Earlier quoted context omitted.

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!

That's not how it works. It's not on everyone else to prove claims false, it's on you (or the people who argue any of this had a measurable impact) to prove it actually works. I've seen a bunch of articles like this, and more comments. Nobody I've ever seen has produced any kind of measurable metrics of quality based on one approach vs another. It's all just vibes. Without something quantifiable it's not much better…

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.

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

#178

Post by vibeprofessor »

add another agent review, I ask Claude to send plan for review to Codex and fix critical and high issues, with complexity gating (no overcomplicated logic), run in a loop, then send to Gemini reviewer, then maybe final pass with Claude, once all C+H pass the sequence is done

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

#179

Post by dnautics »

wokwokwok wrote: post #151

This is the way. The practice is: - simple - effective - retains control and quality Certainly the “unsupervised agent” workflows are getting a lot of attention right now, but they require a specific set of circumstances to be effective: - clear validation loop (eg. Compile the kernel, here is gcc that does so correctly) - ai enabled tooling (mcp / cli tool that will lint, test and provide feedback immediately) - ove…

It's more or less what comes out of the box with plan mode, plus a few extra bits?

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

#180

Post by girvo »

cowlby wrote: post #149
girvo wrote: post #142

Earlier quoted context omitted.

> But the aha moment for me was what’s maintainable by AI vs by me by hand are on different realms. So maintainable has to evolve from good human design patterns to good AI patterns. How do you square that with the idea that all the code still has to be reviewed by humans? Yourself, and your coworkers

I picture like semi conductors; the 5nm process is so absurdly complex that operators can't just peek into the system easily. I imagine I'm just so used to hand crafting code that I can't imagine not being able to peek in. So maybe it's that we won't be reviewing by hand anymore? I.e. it's LLMs all the way down. Trying to embrace that style of development lately as unnatural as it feels. We're obv not 100% there yet…

Then who is responsible when (not if) that code does horrible things? We have humans to blame right now. I just don’t see it happening personally because liability and responsibility are too important
Post reply on HN