News for hackers. Stuff that matters.
Re:The Download: why AI's latest breakthroughs and fears may... by tomrod on Wednesday September 23, 2026 @08:15AM (#49814949)
> Do you write perfect code?

For simple things, occasionally!

For more complex things, usually not, but I write working code. LLMs will sometimes write working code, sometimes not.

Re:The Download: why AI's latest breakthroughs and fears may... by diidjdicksodksk on Wednesday September 23, 2026 @08:34AM (#49815148)
> For simple things, occasionally!

No, you don’t because there’s no such thing.

Re:The Download: why AI's latest breakthroughs and fears may... by tomrod on Wednesday September 23, 2026 @10:13AM (#49816518)
This is easily proven incorrect unless you assume overly draconian definitions of "perfect".

```python

print("hello world!")

```

runs exceptionally well. Bullet-proof in all use cases I've needed it.

Re:The Download: why AI's latest breakthroughs and fears may... by oskdkdjejdj on Wednesday September 23, 2026 @10:25AM (#49816697)
This is also easily proven incorrect when you start to analyse how “print” works and wether it stands to be improved in any way.

No. No code is “perfect”.

Re:The Download: why AI's latest breakthroughs and fears may... by tomrod on Wednesday September 23, 2026 @11:17AM (#49817452)
Aye, a draconian view of the "perfect."
Re:The Download: why AI's latest breakthroughs and fears may... by kdkdkcjejf on Wednesday September 23, 2026 @11:45AM (#49817851)
As opposed to… the lenient view of “perfect”? Perfection is a binary state, either something is or it isn’t. What is /defined/ as perfect in a given context is subject to change, but the meaning of the word is absolute.
Re:The Download: why AI's latest breakthroughs and fears may... by tomrod on Wednesday September 23, 2026 @01:11PM (#49819324)
I love that we are debating the platonic perfect form of perfect.
Re:The Download: why AI's latest breakthroughs and fears may... by ahtcx on Wednesday September 23, 2026 @12:39PM (#49818766)
Nobody is earning a living writing hello world programs, and in real programs perfection doesn't exist. Perfection is at best a widely-held opinion.
Re:The Download: why AI's latest breakthroughs and fears may... by tomrod on Wednesday September 23, 2026 @02:13PM (#49820210)
Two thoughts:

1. Since when do people write code solely for the purpose of earning a living?

2. Yes. I agree that with complex programs, perfection doesn't exist -- mostly a composition paradox issue though, IMO!

Re:The Download: why AI's latest breakthroughs and fears may... by ahtcx on Wednesday September 23, 2026 @08:50AM (#49815296)
If you haven't tried any of the newer models from the last ~6 months, you're out of touch. A year ago, LLMs were essentially just a clever search engine for me, I found they fell apart pretty quickly on bigger codebases and more complex projects.

It doesn't always write perfect code on a first pass but nor do you, and it's amazing at understanding any issues it may encounter, even very low level ones. I don't think there's anything I can do that it can't now. There is a learning curve to working well with LLMs, but once you get there you'll be producing high quality code faster than you can imagine.

Part of me wishes they weren't so good. I enjoy(ed?) the process of working through problems and it does mean you might no longer have a perfect mental model of your code. But I do also enjoy being able to build things well and fast.

Re:The Download: why AI's latest breakthroughs and fears may... by tomrod on Wednesday September 23, 2026 @10:14AM (#49816543)
Opus 5.1 was just so darn verbose and overtuned. I look forward to trying out the new Luna/Sol and recent Claude fixes.
Re:The Download: why AI's latest breakthroughs and fears may... by ahtcx on Wednesday September 23, 2026 @11:39AM (#49817769)
Yeah to be honest I still find Claude too verbose with Fable 5.1, I much prefer the output style of OpenAI's models. With strict guidelines it can be improved but it tends to drift in longer conversations.