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

351–360 of 630 posts

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

#351

Post by girvo »

therealdrag0 wrote: post #251
girvo wrote: post #180

Earlier quoted context omitted.

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

For some software, sure but not most. And you don’t blame humans anyways lol. Everywhere I’ve worked has had “blameless” postmortems. You don’t remove human review unless you have reasonable alternatives like high test coverage and other automated reviews.

We still have performance reviews and are fired. There’s a human that is responsible.

“It’s AI all the way down” is either nonsense on its face, or the industry is dead already.

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

#352

Post by vntok »

BoredPositron wrote: post #317
shevy-java wrote: post #311

Earlier quoted context omitted.

Alchemy involved a lot of do-it-yourself though. With AI it is like someone else does all the work (well, almost all the work).

It was mainly a jab at the protoscientific nature of it.

Reproducing experimental results across models and vendors is trivial and cheap nowadays.

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

#353

Post by aitchnyu »

EastLondonCoder wrote: post #338

I don’t use plan.md docs either, but I recognise the underlying idea: you need a way to keep agent output constrained by reality. My workflow is more like scaffold -> thin vertical slices -> machine-checkable semantics -> repeat. Concrete example: I built and shipped a live ticketing system for my club (Kolibri Tickets). It’s not a toy: real payments (Stripe), email delivery, ticket verification at the door, frontend…

Now that code is cheap, I ensured my side project has unit/integration tests (will enforce 100% coverage), Playwright tests, static typing (its in Python), scripts for all tasks. Will learn mutation testing too (yes, its overkill). Now my agent works upto 1 hour in loops and emits concise code I dont have to edit much.

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

#354

Post by Sammi »

jsmith99 wrote: post #287
koevet wrote: post #282

Has anyone found a efficient way to avoid repeating the initial codebase assessment when working with large projects? There are several projects on GitHub that attempt to tackle context and memory limitations, but I haven’t found one that consistently works well in practice. My current workaround is to maintain a set of Markdown files, each covering a specific subsystem or area of the application. Depending on the ta…

Whenever I build a new feature with it I end up with several plan files leftover. I ask CC to combine them all, update with what we actually ended up building and name it something sensible, then whenever I want to work on that area again it's a useful reference (including the architecture, decisions and tradeoffs, relevant files etc).

Yes this is what agent "skills" are. Just guides on any topic. The key is that you have the agent write and maintain them.

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

#356

Post by Sammi »

irthomasthomas wrote: post #340

In my own tests I have found opus to be very good at writing plans, terrible at executing them. It typically ignores half of the constraints. https://x.com/xundecidability/status/2019794391338987906?s=2... https://x.com/xundecidability/status/2024210197959627048?s=2...

1. Don't implement too much at at time

2. Have the agent review if it followed the plan and relevant skills accurately.

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

#358

Post by dakolli »

nostrademons wrote: post #85
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…

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…

You will never convince me that this isn't confirmation bias, or the equivalent of a slot machine player thinking the order in which they push buttons impacts the output, or some other gambler-esque superstition.

These tools are literally designed to make people behave like gamblers. And its working, except the house in this case takes the money you give them and lights it on fire.

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

#360

Post by BoredPositron »

vntok wrote: post #352
BoredPositron wrote: post #317

Earlier quoted context omitted.

It was mainly a jab at the protoscientific nature of it.

Reproducing experimental results across models and vendors is trivial and cheap nowadays.

Not if anthropic goes further in obfuscating the output of claude code.
Post reply on HN