Hacker News: mirsadm

New comment by mirsadm in "DeepSeek 4 Flash local inference engine for Metal"

mirsadm — Thu, 07 May 2026 19:27:00 +0000

I've built something like this. One issue is that LLMs are actually terrible at writing good shaders. I've spent way too much time trying to get them not to be so awful at it.

New comment by mirsadm in "Pro Max 5x quota exhausted in 1.5 hours despite moderate usage"

mirsadm — Mon, 13 Apr 2026 06:33:25 +0000

The way Claude/Codex behave is entirely consistent with how every vibe coded project (of mine) has ended up so far. I bet those guys have no idea what's going on and are taking guesses because no one understands the thing they've made.

New comment by mirsadm in "Small models also found the vulnerabilities that Mythos found"

mirsadm — Sat, 11 Apr 2026 18:19:53 +0000

How is that going to find anything that interacts across files?

New comment by mirsadm in "System Card: Claude Mythos Preview [pdf]"

mirsadm — Tue, 07 Apr 2026 21:50:56 +0000

The numbers only go up to 100% though.

New comment by mirsadm in "We rewrote our Rust WASM parser in TypeScript and it got faster"

mirsadm — Sat, 21 Mar 2026 13:40:34 +0000

Not in my experience. They're pretty good at getting average performance which is often better than most programmers seem to be willing to aim for.

New comment by mirsadm in "An industrial piping contractor on Claude Code [video]"

mirsadm — Sat, 21 Mar 2026 09:56:53 +0000

I've noticed even experienced engineers have started overestimating how long things would take to build without AI. Believe it or not we coded before AI and not everything took years all the time.

New comment by mirsadm in "If you thought code writing speed was your problem you have bigger problems"

mirsadm — Tue, 17 Mar 2026 20:10:59 +0000

I don't know if I agree with that. It's a struggle to get a modern compiler to vectorize a basic loop.

New comment by mirsadm in "Coding after coders: The end of computer programming as we know it?"

mirsadm — Sat, 14 Mar 2026 07:10:15 +0000

That is already the struggle. There is too much stuff already.

New comment by mirsadm in "The changing goalposts of AGI and timelines"

mirsadm — Sun, 08 Mar 2026 17:32:11 +0000

Why? Give it a couple weeks and everybody will forget about this. They'll be earning more money than previously. Job well done.

New comment by mirsadm in "LLMs work best when the user defines their acceptance criteria first"

mirsadm — Sat, 07 Mar 2026 09:55:22 +0000

100% dependent on the person driving it

New comment by mirsadm in "LLMs work best when the user defines their acceptance criteria first"

mirsadm — Sat, 07 Mar 2026 09:49:48 +0000

I do this all the time but then you end up with really over engineered code that has way more issues than before. Then you're back to prompting to fix a bunch of issues. If you didn't write the initial code sometimes it's difficult to know the best way to refactor it. The answer people will say is to prompt it to give you ideas. Well then you're back to it generating more and more code and every time it does a refactor it introduces more issues. These issues aren't obvious though. They're really hard to spot.

New comment by mirsadm in "Labor market impacts of AI: A new measure and early evidence"

mirsadm — Fri, 06 Mar 2026 11:19:53 +0000

I have already been doing this. I could keep doing it but I'm not going to. I want to be able to understand my own code because that is what let's me make sound higher level decisions.

New comment by mirsadm in "Labor market impacts of AI: A new measure and early evidence"

mirsadm — Fri, 06 Mar 2026 11:12:31 +0000

My own observation is that the initial boost to productivity results in massive crippling technical debt.

New comment by mirsadm in "Labor market impacts of AI: A new measure and early evidence"

mirsadm — Fri, 06 Mar 2026 11:02:03 +0000

I have an app which is fairly popular. This release cycle I used Claude Code and codex to implement all the changes / features. It definitely let me move much quicker than before.

However now that it's in the beta stage the amount of issues and bugs is insane. I reviewed a lot of the code that went in as well. I suspect the bug fixing stage is going to take longer than the initial implementation. There are so many issues and my mental model of the codebase has severely degraded.

It was an interesting experiment but I don't think I would do it again this way.

New comment by mirsadm in "Inside the M4 Apple Neural Engine, Part 1: Reverse Engineering"

mirsadm — Mon, 02 Mar 2026 14:41:43 +0000

Even then there is no transparency on how it decides what runs on the ANE/GPU etc

New comment by mirsadm in "Show HN: Timber – Ollama for classical ML models, 336x faster than Python"

mirsadm — Mon, 02 Mar 2026 10:26:46 +0000

Isn't the whole point for it to learn what features to extract?

New comment by mirsadm in "What AI coding costs you"

mirsadm — Sat, 28 Feb 2026 15:26:56 +0000

This use to be the most embarrassing thing that could happen. A team member asks you why you did something a certain way during a PR and you can't provide an answer. This seems to be becoming the norm now.

New comment by mirsadm in "Hetzner Prices increase 30-40%"

mirsadm — Mon, 23 Feb 2026 10:41:33 +0000

This is yet to be seen. Certainly feels like I'm more productive but I'm not seeing any faster results. It would be nice for this to be studied more.

New comment by mirsadm in "Why is Claude an Electron app?"

mirsadm — Sat, 21 Feb 2026 23:26:29 +0000

I know Anthropic is burning cash but I'm pretty sure they can afford to pay the developer fees for those platforms.

New comment by mirsadm in "AI adoption and Solow's productivity paradox"

mirsadm — Wed, 18 Feb 2026 08:18:54 +0000

This seems like a bot comment.