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

421–430 of 630 posts

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

#421

Post by fasbiner »

DonHopkins wrote: post #397
exe34 wrote: post #383

Earlier quoted context omitted.

If you want to write something with AI, send me your prompt. I'd rather read what you intend for it to produce rather than what it produces. If I start to believe you regularly send me AI written text, I will stop reading it. Even at work. You'll have to call me to explain what you intended to write.

And if my prompt is a 10 page wall of text that I would otherwise take the time to have the AI organize, deduplicate, summarize, and sharpen with an index, executive summary, descriptive headers, and logical sections, are you going to actually read all of that, or just whine "TL;DR"? It's much more efficient and intentional for the writer to put the time into doing the condensing and organizing once, and review and p…

Yeah but it's not. This a complete contrivance and you're just making shit up. The prompt is much shorter than the output and you are concealing that fact. Why?

Github repo or it didn't happen. Let's go.

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

#422

Post by DonHopkins »

fasbiner wrote: post #421
DonHopkins wrote: post #397

Earlier quoted context omitted.

And if my prompt is a 10 page wall of text that I would otherwise take the time to have the AI organize, deduplicate, summarize, and sharpen with an index, executive summary, descriptive headers, and logical sections, are you going to actually read all of that, or just whine "TL;DR"? It's much more efficient and intentional for the writer to put the time into doing the condensing and organizing once, and review and p…

Yeah but it's not. This a complete contrivance and you're just making shit up. The prompt is much shorter than the output and you are concealing that fact. Why? Github repo or it didn't happen. Let's go.

[flagged]

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

#423

Post by hu3 »

imiric wrote: post #369
guiambros wrote: post #245

Earlier quoted context omitted.

> 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 nondete…

Humans are nondeterministic.

So this is a moot point and a futile exercise in arguing semantics.

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

#424

Post by GrinningFool »

majormajor wrote: post #171
FuckButtons wrote: post #150

Earlier quoted context omitted.

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 moc…

But can you see the difference if you only include "you are a senior engineer"? It seems like the comparison you're making is between "write the tests" and "write the tests following these patterns using these examples. Also btw you’re an expert. "

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

#425

Post by intrasight »

jerryharri wrote: post #413
onion2k wrote: post #239

Earlier quoted context omitted.

if you don't plan perfectly, you'll have to start over from scratch if anything goes wrong This is my experience too, but it's pushed me to make much smaller plans and to commit things to a feature branch far more atomically so I can revert a step to the previous commit, or bin the entire feature by going back to main. I do this far more now than I ever did when I was writing the code by hand. This is how developers…

We're learning the lessons of Agile all over again.

We're learning how to be an engineer all over again.

The authors process is super-close what we were taught in engineering 101 40 years ago.

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

#426

Post by hu3 »

gehsty wrote: post #314
Betelbuddy wrote: post #72

Earlier quoted context omitted.

Its very logical and pretty obvious when you do code generation. If you ask the same model, to generate code by starting with: - You are a Python Developer... or - You are a Professional Python Developer... or - You are one of the World most renowned Python Experts, with several books written on the subject, and 15 years of experience in creating highly reliable production quality code... You will notice a clear impr…

Do you think that Anthropic don’t include things like this in their harness / system prompts? I feel like this kind of prompts are uneccessary with Opus 4.5 onwards, obviously based on my own experience (I used to do this, on switching to opus I stopped and have implemented more complex problems, more successfully). I am having the most success describing what I want as humanly as possible, describing outcomes clearl…

Maybe, but forcing code generation in a certain way could ruin hello worlds and simpler code generation.

Sometimes the user just wants something simple instead of enterprise grade.

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

#427

Post by mstkllah »

Bishonen88 wrote: post #255
puchatek wrote: post #244

Earlier quoted context omitted.

Is it on GH?

It was when I mvp'd it 3 weeks ago. Then I removed it as I was toying with the idea of somehow monetizing it. Then I added a few features which would make monetization impossible (e.g. How the app obtains etf/stock prices live and some other things). I reckon I could remove those and put in gh during the week if I don't forget. The quality of the Web app is SaaS grade IMO. Keyboard shortcuts, cmd+k, natural language…

Would love to check it out too once you put it up.

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

#428

Post by mstkllah »

KellyCriterion wrote: post #291
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…

In Claude Web you can use projects to put files relevant for context there.

And then you have to remind it frequently to make use of the files. Happened to me so many times that I added it both to custom instructions as well as to the project memory.

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

#429

Post by intrasight »

cloudbonsai wrote: post #395
scuff3d wrote: post #106

Earlier quoted context omitted.

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

The evolution of software engineering is fascinating to me. We started by coding in thin wrappers over machine code and then moved on to higher-level abstractions. Now, we've reached the point where we discuss how we should talk to a mystical genie in a box. I'm not being sarcastic. This is absolutely incredible.

And I've been had a long enough to go through that whole progression. Actually from the earlier step of writing machine code. It's been and continues to be a fun journey which is why I'm still working.

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

#430

Post by dr_kretyn »

The post and comments all read like: Here are my rituals to the software God. If you follow them then God gives plenty. Omit one step and the God mad. Sometimes you have to make a sacrifice but that's better for the long term.

I've been in eng for decades but never participated in forums. Is the cargo cult new?

I use Claude Code a lot. Still don't trust what's in the plan will get actually written, regardless of details. My ritual is around stronger guardrails outside of prompting. This is the new MongoDB webscale meme.

Post reply on HN