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

201–208 of 208 posts

Re: Control the Ideas, Not the Code

#201

Post by phmx »

edanm wrote: post #196
danceparty wrote: post #35

Very uncomfortable to read. The proposed idea of not reading the code you ostensibly wrote, doesn’t just challenge the traditional workflow or methodology, it challenges the identity of a programmer itself. For experienced, respected programmers like antirez perhaps reading and writing code truly has just gotten in the way of the ideas, but I cannot identify with that perspective. The devil is in the details, reading…

I don't get this perspective. How much of the source code of the compiler you use did you read? How much of the source code of the standard library of your chosen language did you read? What about the dependencies? How much of the source code of a huge codebase does the average developer read? I don't think any human alive has read the majority of code in huge codebases like Word, Windows, Linux, etc. For almost ever…

The code we've shipped throughout our careers certainly wasn't reviewed only by us. It was reviewed by programmers with more expertise in the relevant area. That's a healthy and efficient division of labor, expertise, and responsibility.

Re: Control the Ideas, Not the Code

#202

Post by throwdbaaway »

am17an wrote: post #90
brunocalza wrote: post #83

> Then I compared the implementation, for correctness, to other systems, finding that other implementations sometimes contained more errors. I researched more, and found that the local inference world is full of subtle errors that accumulate and damage the model output, issues in the attention implementation causing performance slopes after the context is over a certain limit because indexed attention implementations…

Having looked at his code, I doubt this.

Yeah antirez made a lot of big claims in that paragraph. Sounds like a case of AI psychosis.

Re: Control the Ideas, Not the Code

#203

Post by mrsalty »

Antirez's take is bold, and probably very scary for most programmers (and especially for their managers), but I think he's mostly right. I'd even go further: people who don't adapt to this change will be soon left behind, because today things are moving blazingly fast.

This doesn't mean AI-generated code is safe. The key point here (which AR explains well in his latest YT video on his way to the gym :D) is that you still need to master the CS fundamentals. Which means:

- People who master the fundamentals will use AI to move much faster.

- People who don't master the fundamentasl and vibe code will evetually hit a wall,

but most importantly

- People who master the fundamentals but review all the code will move much slower.

Innit?

Re: Control the Ideas, Not the Code

#204

Post by AnimalMuppet »

mrsalty wrote: post #203

Antirez's take is bold, and probably very scary for most programmers (and especially for their managers), but I think he's mostly right. I'd even go further: people who don't adapt to this change will be soon left behind, because today things are moving blazingly fast. This doesn't mean AI-generated code is safe. The key point here (which AR explains well in his latest YT video on his way to the gym :D) is that you s…

Maybe. Depends on how solid the code is in the directions that matter for that code. Does security matter? Real-time performance? Never losing a transaction? Never leaking memory? What matters for the code you're trying to write? Future maintainability? How good is AI at producing code that does not fail in the directions that matter?

People who master the fundamentals but review all the code will move much slower. But they'll be more successful in the medium to long run if they're catching things that matter. (If they aren't, of course, they're just wasting time.)

Re: Control the Ideas, Not the Code

#205

Post by mrsalty »

AnimalMuppet wrote: post #204
mrsalty wrote: post #203

Antirez's take is bold, and probably very scary for most programmers (and especially for their managers), but I think he's mostly right. I'd even go further: people who don't adapt to this change will be soon left behind, because today things are moving blazingly fast. This doesn't mean AI-generated code is safe. The key point here (which AR explains well in his latest YT video on his way to the gym :D) is that you s…

Maybe. Depends on how solid the code is in the directions that matter for that code . Does security matter? Real-time performance? Never losing a transaction? Never leaking memory? What matters for the code you're trying to write? Future maintainability? How good is AI at producing code that does not fail in the directions that matter? People who master the fundamentals but review all the code will move much slower.…

>Does security matter? Real-time performance? Never losing a transaction? Never leaking memory? What matters for the code you're trying to write? Future maintainability?

The assumption I believe is: if you are experienced enough you will instruct your agent(s) to address all of these during your iterations.

Re: Control the Ideas, Not the Code

#206

Post by waynecochran »

hollowturtle wrote: post #189
waynecochran wrote: post #185

Earlier quoted context omitted.

That is the part Claude can handle and actually does. In fact, recently claude automaticaly converted some spline generating code to double precision and did some other refactoring as well after it realized poor results thru tests it generated on its own! I was gobsmacked!

Unimpressive slot machine, it will betray you sooner than later and pay a real price

I am shipping sophisticated computer vision code that is more reliable and better tested than ever before. This isn't some vibe coded bullsh*t. This is me writing detailed mathematical specs and it do all the heavy lifting.

Re: Control the Ideas, Not the Code

#207

Post by AnimalMuppet »

mrsalty wrote: post #205
AnimalMuppet wrote: post #204

Earlier quoted context omitted.

Maybe. Depends on how solid the code is in the directions that matter for that code . Does security matter? Real-time performance? Never losing a transaction? Never leaking memory? What matters for the code you're trying to write? Future maintainability? How good is AI at producing code that does not fail in the directions that matter? People who master the fundamentals but review all the code will move much slower.…

>Does security matter? Real-time performance? Never losing a transaction? Never leaking memory? What matters for the code you're trying to write? Future maintainability? The assumption I believe is: if you are experienced enough you will instruct your agent(s) to address all of these during your iterations.

[dead]

Re: Control the Ideas, Not the Code

#208

Post by huimang »

edanm wrote: post #196
danceparty wrote: post #35

Very uncomfortable to read. The proposed idea of not reading the code you ostensibly wrote, doesn’t just challenge the traditional workflow or methodology, it challenges the identity of a programmer itself. For experienced, respected programmers like antirez perhaps reading and writing code truly has just gotten in the way of the ideas, but I cannot identify with that perspective. The devil is in the details, reading…

I don't get this perspective. How much of the source code of the compiler you use did you read? How much of the source code of the standard library of your chosen language did you read? What about the dependencies? How much of the source code of a huge codebase does the average developer read? I don't think any human alive has read the majority of code in huge codebases like Word, Windows, Linux, etc. For almost ever…

The idea is that -someone- reviewed the lines of code they modified, leading to the sum of code being looked at by many human eyes. Using someone else's code has always been a system of trust in this way.

AI/Vibecoding breaks this social trust, hence the general aversion to using those codebases or bringing LLM code in. It's not really about the general quality of the agents. It's about the code no longer being reviewed and understood by a human. How can one place trust in that? Unit tests don't replace careful review and considerate design.

Post reply on HN