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

361–370 of 630 posts

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

#361

Post by folex »

this is exactly how I work with cursor

except that I put notes to plan document in a single message like:

   > plan quote
   my note
   > plan quote
   my note
otherwise, I'm not sure how to guarantee that ai won't confuse my notes with its own plan.

one new thing for me is to review the todo list, I was always relying on auto generated todo list

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

#362

Post by adithyassekhar »

What I've read is that even with all the meticulous planning, the author still needed to intervene. Not at the end but at the middle, unless it will continue building out something wrong and its even harder to fix once it's done. It'll cost even more tokens. It's a net negative.

You might say a junior might do the same thing, but I'm not worried about it, at least the junior learned something while doing that. They could do it better next time. They know the code and change it from the middle where it broke. It's a net positive.

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

#363

Post by irthomasthomas »

Sammi wrote: post #356
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.

the first link was from a simple request with fewer than 1000 tokens total in the context window, just a short shell script.

here is another one which had about 200 tokens and opus decided to change the model name i requested.

https://x.com/xundecidability/status/2005647216741105962?s=2...

opus is bad at instruction following now.

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

#364

Post by ionwake »

adithyassekhar wrote: post #362

What I've read is that even with all the meticulous planning, the author still needed to intervene. Not at the end but at the middle, unless it will continue building out something wrong and its even harder to fix once it's done. It'll cost even more tokens. It's a net negative. You might say a junior might do the same thing, but I'm not worried about it, at least the junior learned something while doing that. They c…

this comment is the first truly humane one ive read regarding this whole AI fiasco

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

#365

Post by jeleh »

Good article, but I would rephrase the core principle slightly:

Never let Claude write code until you’ve reviewed, *fully understood* and approved a written plan.

In my experience, the beginning of chaos is the point at which you trust that Claude has understood everything correctly and claims to present the very best solution. At that point, you leave the driver's seat.

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

#366

Post by anonymousDan »

adithyassekhar wrote: post #362

What I've read is that even with all the meticulous planning, the author still needed to intervene. Not at the end but at the middle, unless it will continue building out something wrong and its even harder to fix once it's done. It'll cost even more tokens. It's a net negative. You might say a junior might do the same thing, but I'm not worried about it, at least the junior learned something while doing that. They c…

Unfortunately, you could argue that the model provider has also learned something, i.e. the interaction can be used as additional training data to train subsequent models.

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

#368

Post by foldingmoney »

ffsm8 wrote: post #285
vishnugupta wrote: post #269

Earlier quoted context omitted.

Revolutionary or not it was very nice of the author to make time and effort to share their workflow. For those starting out using Claude Code it gives a structured way to get things done bypassing the time/energy needed to “hit upon something that several of us have evolved to naturally”.

Its ai written though, the tells are in pretty much every paragraph.

>the tells are in pretty much every paragraph.

It's not just misleading — it's lazy. And honestly? That doesn't vibe with me.

[/s obviously]

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

#369

Post by imiric »

guiambros wrote: post #245
scuff3d wrote: post #207

Earlier quoted context omitted.

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…

A lot of words to say that for all intents and purposes... it's nondeterministic.

> Yes, it's a departure from the fully deterministic systems we're used to.

A system either produces the same output given the same input[1], or doesn't.

LLMs are nondeterministic by design. Sure, you can configure them with a zero temperature, a static seed, and so on, but they're of no use to anyone in that configuration. The nondeterminism is what gives them the illusion of "creativity", and other useful properties.

Classical computers, compilers, and programming languages are deterministic by design, even if they do contain complex logic that may affect their output in unpredictable ways. There's a world of difference.

[1]: Barring misbehavior due to malfunction, corruption or freak events of nature (cosmic rays, etc.).

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

#370

Post by juanre »

Shameless plug: https://beadhub.ai allows you to do exactly that, but with several agents in parallel. One of them is in the role of planner, which takes care of the source-of-truth document and the long term view. They all stay in sync with real-time chat and mail.

It's OSS.

Real-time work is happening at https://app.beadhub.ai/juanre/beadhub (beadhub is a public project at https://beadhub.ai so it is visible).

Particularly interesting (I think) is how the agents chat with each other, which you can see at https://app.beadhub.ai/juanre/beadhub/chat

Post reply on HN