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

41–50 of 208 posts

Re: Control the Ideas, Not the Code

#41

Post by atoav »

logicprog wrote: post #11
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…

I do highly unusual, off the beaten path projects with AI. For instance, a game engine written entirely in LuaJIT, but allocating almost all data structures using CFFI, a very unusual, custom object-orientation DSL I designed myself, and that uses SDL3's SDL_gpu library to do all rendering, a ton of GLSL 4.6 compute shaders cross compiled to SPIR-V and Metal (which constraints what GLSL can be written), and is a hybr…

It is easier to get an LLM to tell an unusual story using the most popular phrases than have it tell a common story using off-kilter uncommon phrases.

The big arc is easy to get using an LLM, getting it to do the details correctly, that is the actual hard part. So in my cases I (by other people's account a legendarily patient person) lost my cool trying to get a LLM to write CSS in a way that makes any sense if you have a design background. I ended up rewriting the whole CSS by hand, because it is inconsistent, piecemeal and just doesn't make sense. Yeah let's make everything bold and important. Yeah let's write internal implementation details into a label in the UI.

I decided to use LLMs as an aid to my own thinking, not as a replacement.

Re: Control the Ideas, Not the Code

#44

Post by hbcdbff »

This position assumes that purely LLM-written codebases are able to scale infinitely.

IMO there isn’t enough evidence for me to feel comfortable in that judgement.

Anecdotally, I find that pretty often LLMs (even bleeding-edge models) write unidiomatic/unscalable/poorly-abstraced code when working in large codebases.

Re: Control the Ideas, Not the Code

#46

Post by antirez »

krupan wrote: post #38

I think the gist of what the author is saying is, AI is not good enough to just give one vague prompt to and let it go, but it's good enough for you to give it a "design" and then not worry about the actual code it writes. But you need to do a lot of QA still. And you still need to learn to code and write some code, I guess so you can give the LLM good instructions? But if giving good enough instructions requires som…

Never comment till you read the whole post, since your question is exactly addressed at the end.

Re: Control the Ideas, Not the Code

#47

Post by jgeada »

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.

Nothing yet has replaced the curating of ideas that good teams do as a matter of course.

Re: Control the Ideas, Not the Code

#48

Post by inigyou »

Tade0 wrote: post #15
inigyou wrote: post #6

Earlier quoted context omitted.

100% of the employers I worked for since the time of Valkey had replaced Redis with Valkey.

To be honest until today I thought Kafka was the popular go-to Redis replacement, as almost none of my employers used Redis for its original, intended purpose, namely being an in-memory key-value store. What they really wanted was RabbitMQ.

Kafka does a completely different thing than Redis.

Re: Control the Ideas, Not the Code

#49

Post by andsoitis »

> Matteo Collina yesterday asked me, in reply to my tweet: but didn’t you say that you check all the AI generated code for Redis? And this is a good question indeed. Yes, I do, but this is, at this point, something I need to do but that I believe to be mostly pointless, partially once GPT 5.5 was released, but now with Fable and GPT 5.6 Sol even more. Yes: I identify things that I don’t like how they are coded, but if I open other Redis files written by other Redis contributors there is far worse, and not since they are not good coders, but because it is a matter of taste.

I wonder why he HAS TO ("I need to...") review the code even if he thinks it is pointless? Is that because his employer, Redis, requires it?

Re: Control the Ideas, Not the Code

#50

Post by inigyou »

philipallstar wrote: post #23
echelon wrote: post #9

Earlier quoted context omitted.

As a reminder, Amazon and Google pillaged the Redis project and took all the profits of themselves. OSI purity is hyperscaler brainwashing. They don't want to pay you. They want to take your labor. Amazon and Google have made billions of dollars off of Redis while the original authors and the company formed around it have gotten none of that. The best licenses for new database projects are fair source and open core.…

This isn't true, I don't think. For example, Instagram was built on Django, but I don't believe the Django founders magically got money because their totally free to use OSS was used in the way it was licenced. If you don't want people to use your software and make money, then don't release it with a licence that explicitly says you may make money from this software. What was stolen?

There used to be a social contract that you got free code if you behaved nicely with it. Then companies realised social contracts were worthless (not just in open source) and stopped following them and only followed legal contracts.
Post reply on HN