Hacker News: manmal

New comment by manmal in "Nietzschian Debugger"

manmal — Mon, 26 Oct 2026 18:46:07 +0000

I see how this could be useful, to roast agents while they are debugging or building something.

New comment by manmal in "Writing Is Closer to Thought Than Code"

manmal — Mon, 26 Oct 2026 13:31:09 +0000

Why not use gherkin given/when/then stories, and build E2E runners and maybe also unit tests for them? I don’t understand why a new spec format is necessary, which forever binds you to using agents for evaluation. Deterministic tests also have the advantage that they are harder to cheat on. If they are green, they give me a strong signal I can trust.

New comment by manmal in "Iron Age salt-mining complex found beneath Hallstatt in Austria"

manmal — Mon, 26 Oct 2026 12:44:18 +0000

Yes it’s basically unlivable. It’s super small and way too many people want in, every day. It’s also a very beautiful spot and I sometimes crave going to that wider area (Salzkammergut).

New comment by manmal in "Iron Age salt-mining complex found beneath Hallstatt in Austria"

manmal — Mon, 26 Oct 2026 12:42:22 +0000

Salzburg is only 70km from Halstatt, but interestingly that name comes from nearby Reichenhall (Germany), another big salt producer.

New comment by manmal in "We should be more ambitious with the software we build"

manmal — Sun, 25 Oct 2026 16:19:31 +0000

Sure but that’s probably 100x max? It won’t magically work, there’s a lot of (auto) review and verification that has to be carefully setup, so things actually work in the way you need them to. I’ve done it, it takes days until it’s good.

New comment by manmal in "Median product "lifespan" has fallen from ~4y down to ~1.5y"

manmal — Fri, 23 Oct 2026 05:20:57 +0000

Certainly not for infrastructure.

New comment by manmal in "DeepInfer: High-performance inference framework for DeepSeek models"

manmal — Tue, 20 Oct 2026 21:54:49 +0000

Isn’t the Muse team just 200 people? I guess you don’t need that much work done.

New comment by manmal in "Advanced coding in low-resource programming languages"

manmal — Tue, 20 Oct 2026 19:08:15 +0000

Except for platform constraints, like needing to use JS or Swift/Kotlin, why would I use anything else than Rust? I can’t even properly read it, but the agents somehow make it work well and the code doesn’t look particularly cluttered; and it’s so fast.

New comment by manmal in "MiniMax M3.1 Flash"

manmal — Mon, 19 Oct 2026 19:37:04 +0000

Isn’t input so much cheaper because it’s just less work? Prefill is usually 10-20x as fast as generation.

If you have 200k context, but only 200t/s prefill, then you’ll wait multiple minutes when continuing an average session from yesterday. Or compaction - might take 15 minutes.

New comment by manmal in "The Elizabeth Holmes documentary “You Can See Everything” is deceiving"

manmal — Sun, 18 Oct 2026 14:18:23 +0000

It’s this year’s most memed trailer. It’s also where the wide eyed Elizabeth meme comes from.

New comment by manmal in "Tesla Roadster"

manmal — Sat, 17 Oct 2026 06:18:54 +0000

Not even hopping. Just tilt/lift the car through the tight spot.

New comment by manmal in "I know why the mathematicians weep"

manmal — Thu, 15 Oct 2026 19:05:09 +0000

> the removal of all human leverage via their labor

I’m not convinced at all that SI will ever be able to produce the correct result with little input. The advancements in capability I’ve seen in models is that they understand my intention better, and follow industry best practices better, so their output is often acceptable. But I absolutely have to make my intentions known, as detailed as possible, or I will get the mediocre, standard solution that falls out of the weights.

I’ve been having trouble with models always steering towards certain solutions - they insert a queue here, a mutex there, a backoff over there. If I remove those, and let the model freely rebase the PR stack, then it will re-insert those mechanisms because it has been specifically trained to do exactly that. It’s essentially boilerplate, smoothly aligning my codebase to match their weights. Which is often good enough! They are training the models well. But individual problems require individual solutions.

My personal take on the human part in all this is: We get to decide, and the models obey. Our decisions are now super leveraged. So let’s make good decisions, and communicate them well. The layer of where decisions yield the most leverage, has been pushed upwards (I see it on the type and function signature level, others will see it even higher), but IMO it won’t be possible to push it up much further without losing truth to the decisions we need to make for a good product.

New comment by manmal in "Steam Client is now faster than Epic's new vibe coded launcher"

manmal — Thu, 15 Oct 2026 16:22:49 +0000

It’s just that the vibe coded stuff has so many assumptions baked in, that you will be constantly surprised about the behaviors your slopped codebase has. Doesn’t matter for small tools, where you’ll be delighted that clicking that one label copies it to your clipboard - nice one, Claude, that’s delightful!

It’s less nice when your web app launches that other service only when the other Tailscale node is up, because the agent interpreted your prompt as a hard access rule.

New comment by manmal in "Do dentists know what they're doing?"

manmal — Wed, 14 Oct 2026 19:01:47 +0000

I had a small hole filled at age 18. The guy drilled too fast/hot, which damaged the tooth, a few years later it specularly died (abscess under the crown etc) and had to be pulled. It probably was only a discoloration because the other teeth held up perfectly, for another decade.

New comment by manmal in "The gap in shared understanding of LLM capability is widening"

manmal — Mon, 12 Oct 2026 16:50:34 +0000

Lauren Tan from SpaceXAI/Cursor/Grok has been on a few podcasts recently. I was surprised how much info she shared, and she sounded quite honest about what works and what doesn’t, in the context of building grokbot. I wouldn’t be able to do all the verifications she does, with my token budget. But it doesn’t seem like rocket science either (pun not intended).

New comment by manmal in "I'm sorry, but you still have to think"

manmal — Sun, 11 Oct 2026 20:16:34 +0000

Sounds like Claude. I haven’t made this experience with the large OpenAI models.

New comment by manmal in "Grieving the loss of details"

manmal — Sun, 11 Oct 2026 14:01:21 +0000

> You know what a byte is, you know the endianness, the signedness, you can feel comfort in knowing you're not missing anything, and then you build up from there seeing each block build upon the previous.

IMO you’ve chosen a flight level you’re comfortable with (which is fine!) but there is much going on below the abstraction that lets you view a file as a bag of bytes.

I’m saying this as someone who uses SwiftUI and CoreBluetooth on a daily basis, and I have to trust these foundations just as you seem to trust the C compiler and a filesystem.

New comment by manmal in "Grieving the loss of details"

manmal — Sun, 11 Oct 2026 13:45:25 +0000

My comment wasn’t about LLM vs compiler, but about low level libraries vs high level libraries.

New comment by manmal in "Grieving the loss of details"

manmal — Sun, 11 Oct 2026 13:41:47 +0000

Sure, but if you yourself can intuit how to find all 41, why can’t a clanker?

New comment by manmal in "Grieving the loss of details"

manmal — Sun, 11 Oct 2026 11:21:56 +0000

> fully defining a deterministic check is the same as finding them all

That’s like saying mathematics is worthless and we have to resort to finger counting?