Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Control the Ideas, Not the Code

antirez.com

Post reply on HN
Print view View original

131–140 of 208 posts

Re: Control the Ideas, Not the Code

#131

Post by softwaredoug »

antirez wrote: post #124
jgeada wrote: post #47

Ideas are a dime a dozen. All of us have half a dozen of what appear to be good ideas every. Execution matters, testing and sanity checking matters, actual engagement with users and iteration matters. Sure, we're reducing the cost of idea -> prototype to near zero (well, as long as tokens are free or nearly free), but that just means we now have mountains of throw away code, within which there may a gem or two. Nothi…

Execution is not the code, but how do you decide to do every part. "Idea does not matter, execution does" always meant: "big generic ideas don't matter, it is how you organize it in the myriad of details it is composed of (in a given incarnation of the general idea) that matters."

But why aren't lower level "ideas about execution" more clearly expressed in code? Or at least pseudocode?

Many of us would struggle with our reading comprehension of an English description of an algorithm. But the pseudo / actual code? Much easier to reason about.

I'm not saying you should review even 90% of code. But it feels like an arbitrary line to say "never look at code". It's like never taking a wrench to a car to look at what's built to see whether you trust the car factory.

Re: Control the Ideas, Not the Code

#132

Post by logicprog »

fzeroracer wrote: post #119
ssivark wrote: post #40

Earlier quoted context omitted.

> All I can say is skill issue I know nothing about you or your code, but till you make your code + workflows public and have all of it reviewed / critiqued (so that other can replicate the performance), it's hard to accept it as a serious case study. For all we know, this could just as well be a severe case of Dunning-Kruger.

I've found this to be more consistently the case than not. People almost never post their project and in the rare cases that they do, it's usually some shambling mess that doesn't actually function. They put together a keyword soup post that sounds good on an AI generated resume but falls apart upon investigation.

Its hard not to feel insulted here. "Projects using AI like this don't exist, and if they do, they're broken and the people who made them have psychosis." However, although I haven't tested my projects cross machine, or cross platform yet (my editor only works on MacOS because it uses kqueue), I would be happy to take an unedited video demonstration of both, I assure you they both run.

Re: Control the Ideas, Not the Code

#133

Post by dominotw »

logicprog wrote: post #126
dominotw wrote: post #115

Earlier quoted context omitted.

things you described are not "highly unusual" in the way gp comment is describing. you are just remixing bunch of stuff. Thats the type of thing ai is really good at.

The GP was just talking about not using common languages like TypeScript and frameworks like React, which is a bar of unusual that seems arguably far lower than mine, especially since I literally defined special custom DSLs with unusual semantics, and used libraries like SDL_gpu with little to no pre-existing training data. So this seems like shifting the goalposts. Also, what would be highly unusual to you?

> The GP was just talking about not using common languages like TypeScript and frameworks like React

i dont see anything like that in that comment.

Re: Control the Ideas, Not the Code

#134

Post by TZubiri »

Author is redis dev. Seems deep in vibecode mode

Genuine question, is redis actually used by competent engineers?

The idea of a separate networked process to store and retrieve variables from memory sounds like something a first year engineer would do when they learn about a hot tech netflix uses before they learn about fundamentals like what a heap and a stack are.

Re: Control the Ideas, Not the Code

#135

Post by cyanydeez »

m_ke wrote: post #54
cyanydeez wrote: post #34

Earlier quoted context omitted.

right, the model will listen to you for ~32k context; half of that is just getting them into the "downhill" path for being a coding assistant. You can throw in whatever your heart's desire and if it's a single fix, it might listen to you; but treating it like a smart-IDE basically means it'll follow whatever dominant pattern is in the training data. If we had smart capitalism (the SAME PROBLEM) we'd realize what we w…

yeah I tried rules, hooks and forbidding things like pip / python3 but it just led to the model failing to do what it wants and a bunch of token churn trying to get around my more rigid constraints. main problem is that the harness files get loaded into context early in the session and slowly wash away as new information comes in.

i've been playing around with https://github.com/bytedance/deer-flow and they seem to figure out how to get around context sizing issues and has a more automated prompt system.

Essentially the problem with current hanrsses is they just can't find/evict context and want to ensure KV cache isn't evicted.

If they evict the old prompt and tried to keep all the proper rules, then you get token churn anyway, as what you want is an entirely new chain of events where your rules/guidance sit at the front of the model chain.

What we're getting to is there really isn't an economical way for cloud models to do it; you can do it with a local model, but at comfortable speeds, you need smaller sized.

I think a good harness via Qwen3.6-35B-A3B is possible, as the token gen is only 3B since that's the active parameters.

So it's mostly that to keep rules pinned to the top of the context will either bloat the model or it'll evict the KV cache.

Re: Control the Ideas, Not the Code

#136

Post by logicprog »

dominotw wrote: post #133
logicprog wrote: post #126

Earlier quoted context omitted.

The GP was just talking about not using common languages like TypeScript and frameworks like React, which is a bar of unusual that seems arguably far lower than mine, especially since I literally defined special custom DSLs with unusual semantics, and used libraries like SDL_gpu with little to no pre-existing training data. So this seems like shifting the goalposts. Also, what would be highly unusual to you?

> The GP was just talking about not using common languages like TypeScript and frameworks like React i dont see anything like that in that comment.

"It's not an issue of usual vs unusual, I'm saying the models are way better at writing and maintaining django or react code bases than your own hand rolled architecture that you define in some docs that it has to learn and keep in context. All of the models do an amazing job making local edits and working in small greenfield projects but once you get to full production systems with close to a million lines things start to rot. The code still works and the models are able to make progress but all of a sudden you have 3-4 different versions of your concepts sprinkled in random corners of your code base.

My second point is that the models are way better at things like Rust or Lua than Python or JS, because the average person producing code in those languages has way more programming experience"

Re: Control the Ideas, Not the Code

#137

Post by iwontberude »

m_ke wrote: post #2

I tried really hard to do this, but it turns out the models don't care about your ideas and want to do what's popular in their training data, so they will happily ignore anything you try to force down their throats, especially as context length grows or if you hit compaction. So to make best use of the models steer them down familiar paths, mention common pattern and frameworks, use popular packages and languages tha…

It makes everyone more average and same-y. It’s a good average, better than bad, but I cringe everytime I see someone claiming it’s a force multiplier for their personal expression. Bullshit.

Re: Control the Ideas, Not the Code

#138

Post by jryle70 »

fzeroracer wrote: post #119
ssivark wrote: post #40

Earlier quoted context omitted.

> All I can say is skill issue I know nothing about you or your code, but till you make your code + workflows public and have all of it reviewed / critiqued (so that other can replicate the performance), it's hard to accept it as a serious case study. For all we know, this could just as well be a severe case of Dunning-Kruger.

I've found this to be more consistently the case than not. People almost never post their project and in the rare cases that they do, it's usually some shambling mess that doesn't actually function. They put together a keyword soup post that sounds good on an AI generated resume but falls apart upon investigation.

> People almost never post their project and in the rare cases that they do, it's usually some shambling mess that doesn't actually function

It's funny because you chose to target the one who is pro-AI, who has since posted their code, and not the GP who is against AI, who also didn't post any code to support his opinion that "it turns out the models don't care about your ideas and want to do what's popular in their training data".

Do you see the irony?

Re: Control the Ideas, Not the Code

#139

Post by logicprog »

jryle70 wrote: post #138
fzeroracer wrote: post #119

Earlier quoted context omitted.

I've found this to be more consistently the case than not. People almost never post their project and in the rare cases that they do, it's usually some shambling mess that doesn't actually function. They put together a keyword soup post that sounds good on an AI generated resume but falls apart upon investigation.

> People almost never post their project and in the rare cases that they do, it's usually some shambling mess that doesn't actually function It's funny because you chose to target the one who is pro-AI, who has since posted their code, and not the GP who is against AI, who also didn't post any code to support his opinion that "it turns out the models don't care about your ideas and want to do what's popular in their…

No, they don't. They're more interested in pathologizing and talking down to and about me.

Re: Control the Ideas, Not the Code

#140

Post by fnoef »

Very egocentric piece. Almost reads as “I’m so cool, I did so many cool things, and most things other people did is way worse than even the slop that my LLM prompting skills are capable to produce”.

Also “ You have to understand how things work, what is the best design, how to reach a certain level of performance.” - how does OP propose to understand how things work or what is the best design if you don’t actually go and build things or read the code? I hope the answer is not “reading mythical man month” or “watching YouTube video tutorials”.

Post reply on HN