News for hackers. Stuff that matters.
Re:Mistral Large 4 by user43928 on Tuesday October 06, 2026 @10:25AM (#49979025)
Many on HN still have the opinion that you must understand every line of code in the project, and that all is lost should you merge code that wasn't reviewed.

Obviously any model will do if you use it as a better autocomplete.

I believe that there is a large gap in expectations between different workflows.

Until the AI like reads my mind and produces perfectly production ready apps with minimal intervention from my side, there is still going to be room for improvement.

Re:Mistral Large 4 by RealityVoid on Tuesday October 06, 2026 @05:01PM (#49984094)
> Many on HN still have the opinion that you must understand every line of code in the project, and that all is lost should you merge code that wasn't reviewed.

Uhm, yes?

Re:Mistral Large 4 by kragen on Tuesday October 06, 2026 @07:48PM (#49985843)
Last week I elicited a parametric 3-D design model of a sand battery, a simplified thermal circuit model of it for rough exploration, a backward Euler multiphysics solver to evaluate its performance more accurately, and a volumetric visualization for the resulting temperature distributions, including some custom WebGL shaders: http://canonical.org/~kragen/sw/sandbattery/

It's about 12000 lines of code. I could probably understand every line of it if I spent a couple of months on it, although I'd need to learn some things about WebGL, numerical computation, and solid-state physics. But I elicited it in four days. Probably I'd be better off spending the next couple of months doing something else instead.

So, I was faced with the question of how I could keep the artifact thus created from being completely valueless. My solution was to export the heat-equation solution produced by the solver as (gzipped!) CSV, so that I can use my own code (that I do understand every line of!) to check that the solutions found by the solver are, in fact, solutions.

If that check checks out, the backward Euler solver may be of some value even if I don't understand every line of it.

Re:Mistral Large 4 by pimeys on Tuesday October 06, 2026 @06:56PM (#49985347)
How I feel it Opus 5.5 and Astra 6 are both quite disappointing. They still write shit Rust. And they are very slow.

Now my provider serves DeepSeek around 300 tokens a second. The code is shit but I can have a few more rounds of corrections.

DeepSeek was maybe a dollar for the full PR. Opus/Astra over 50 dollars. And double that if you use their fast variants which matches the DeepSeek speeds on certain providers.

Yes, it is so good I rarely test new models anymore. Or think about cost.

Re:Mistral Large 4 by ashdksnndck on Tuesday October 06, 2026 @11:56PM (#49987957)
The Rust I’m getting from Opus 5.5 works great. What’s the complaint?

Actually I felt since 4.5, it was “good enough” for basic coding (and competing models have reached that level as well). The big improvements since then have been longer-horizon tasks. Giving it a vague description of a problem, then come back hours later and find it did a better job than I would have. And since 5.5 I haven’t encountered any more load bearing seams.

Maybe it’s slow, but I’m not interacting with the models in a live chat anymore for most work. I’m giving them tasks to do async. The limiting factor is actually my bandwidth reviewing their output.

Re:Mistral Large 4 by pimeys on Wednesday October 07, 2026 @03:08AM (#49989357)
> You're absolutely right, I should not use a global mutex.

I am eyeing a huge codebase built with Opus. Did multiple passes of refactoring for things like using traits not just free functions. And using the Rust types like PathBuf from the damn standard library not just strings everywhere.

Oh and it is so hard to use a crate. Let's just vibe an inferior version and push another 5k line PR. Nobody reads them anyway right? Logos schlogos, a lexer is easy to write, right?

Maybe I am just getting old, but I remember a time when we were proud on the code we wrote. Now I read some of the old stuff and get a bit sad for what we lost.

Don't get me wrong DeepSeek also does this. But if the model is 100x more expensive I expect better. Of course if you never read the code it's ok. But it does the same mistakes and cannot design great architecture...

Re:Mistral Large 4 by ashdksnndck on Wednesday October 07, 2026 @02:11PM (#49996599)
Hmm, I wonder if the difference is that I’m working on an existing large codebase that wasn’t originally written with AI. It might be picking up practices from the surrounding code. It’s happily using the same crates that are already there, and occasionally bringing in new ones. Some of the code is “weird” but I also learn from it.