Hacker News: laszlojamf

New comment by laszlojamf in "No–AI Agents Did Not Build Secret Civilizations Stop Anthropomorphizing Malware"

laszlojamf — Thu, 03 Sep 2026 08:20:39 +0000

I don't know, man. Saying this is "just malware" is really stretching the definition of malware. At a minimum this is some pretty interesting and/or terrifying emergent behavior

New comment by laszlojamf in "What sort of maths are LLMs good at?"

laszlojamf — Wed, 12 Aug 2026 11:26:57 +0000

for somebody who's out of the loop: what's the fuss over the ABC conjecture?

New comment by laszlojamf in "Go is an ideal language for AI-assisted software engineering"

laszlojamf — Wed, 12 Aug 2026 05:45:35 +0000

I use go for work and basically 100% agent-driven. I'd say using go with agents is a lot better than without. We use to have a consistent source of production errors where we forgot the pointer case in type switches (we'd pass a pointer to a struct where a concrete struct was expected and vice versa). AI hasn't made that mistake once in my experience.

That being said, the whole thing about go being "readable" is a little bit of a two-edged sword. Sure, it's straight-forward to read, but it's pretty verbose. And agents are good at producing a lot of text. The problem with reviewing go code for me is to see the forest for the trees. Subtle misunderstandings often hide in the vast amount of code that you have to read through while keeping the whole context in your head.

New comment by laszlojamf in "Learning more about Claude's mathematical capabilities"

laszlojamf — Tue, 11 Aug 2026 08:49:41 +0000

60 subagents for a day and a half. I guess he's not on the same plan I am on.

New comment by laszlojamf in "Three Six Mafia – Data about "6/6/6 dating" (2024)"

laszlojamf — Thu, 06 Aug 2026 09:35:48 +0000

Now I'm not wont to ogle much in the swimming pool showers, but in my limited ocular estimation, wang size correlates much weaker than hands and feet.

New comment by laszlojamf in "Show HN: Wallfacer – A terminal session manager for Claude Code, and more"

laszlojamf — Thu, 06 Aug 2026 05:56:55 +0000

The name is pretty ominous if you've read the Three Body Problem series. I don't want my agents planning against me in secrecy.

Just out of curiosity, why did you pick that name? Is there anything wallfacey about this project I'm not getting?

New comment by laszlojamf in "There Will Come Soft Rains (1950) [pdf]"

laszlojamf — Tue, 04 Aug 2026 12:03:17 +0000

The most interesting thing about science fiction to me isn't the things the authors get right, but what they get wrong. Like, the whole house talking in a ChatGPT voice, intelligent appliances, etc: brilliant prescience. But he still thought we'd be having linoleum on our floors...

New comment by laszlojamf in "Qwen3.8-Max: A New Bar for Coding and Cowork"

laszlojamf — Mon, 03 Aug 2026 13:48:41 +0000

in general with automated code reviews I've found it fruitful to tell the model what specifically to look for and where. I usually don't get over 10% of the claude opus context window for code reviews, but it of course depends on how your code is structured, how much the agent has to explore etc.

New comment by laszlojamf in "Qwen3.8-Max: A New Bar for Coding and Cowork"

laszlojamf — Mon, 03 Aug 2026 13:46:06 +0000

What was it reviewing? Was it just a "take a look at this pile of code over here"? Because I think asking any model to review 30M lines of code is a stretch...

New comment by laszlojamf in "The AI Productivity Gap"

laszlojamf — Mon, 03 Aug 2026 08:54:28 +0000

What I have noticed in my own work that a lot of the time that used to be for coding is now just waiting. I have three agents working on three different features in parallel, and I'll go back and forth with all of them, correcting things and steering etc, but then I find myself with three busy agents and nothing to myself except stare at the screen while they code away. There is a mental budget for me where I can't have more than those three running at the same time and still keep track so what I end up doing is just scrolling HN...

New comment by laszlojamf in "After the AI Crash"

laszlojamf — Wed, 29 Jul 2026 14:34:21 +0000

I've been reading a lot of stories like this lately. I'm no business genius, but you'd assume that investors are. Are they just blind or are they burning cash on purpose. What's the steelman argument here?

New comment by laszlojamf in "After the AI Crash"

laszlojamf — Wed, 29 Jul 2026 14:31:45 +0000

a friend of mine did a high school project where he and a friend learnt it well enough to have a short conversation with each other. That's the only time it has come up in life until now. I hope he sees this.

New comment by laszlojamf in "A missing underscore sent innocent man to prison for 18 months"

laszlojamf — Tue, 28 Jul 2026 09:08:44 +0000

The scary thing is that it's unclear to me what would have happened if the guy hadn't had a Kik account, and the real perp had used just one underscore. Can you just pick somebody's username from another service to frame them for grooming? Couldn't you do this to anyone in that case, if that's all that it takes? I sure hope this article is leaving something out, otherwise this is some kangaroo court shit...

New comment by laszlojamf in "Escape IntelliJ: Scala and Kotlin LSPs on Emacs Eglot"

laszlojamf — Thu, 23 Jul 2026 11:13:54 +0000

I agree that IntelliJ is a monster of a resource hog, but I have yet to find an editor where code navigation is as good. That's basically all I use it for these days, in the days of LLMs, and I still think it's worth it. VSCode, especially for golang, is terrible. I might be holding it wrong, but I've really tried, and it's just not good enough.

Before LLMs, when I still refactored by hand, coworkers who were using vim or vscode used to ask me to do big refactors, because IntelliJ always got it right, whereas with the other editors it was hit-or-miss.

New comment by laszlojamf in "Original Apollo 11 Guidance Computer source code for command and lunar modules"

laszlojamf — Wed, 22 Jul 2026 14:06:30 +0000

As other commenters have pointed out, some of the comments in there are pretty scary. I guess the astronauts didn't have to read the code:

`TC WHIMPER -1 # YES. DONT DO POODOO. DO BAILOUT.`

New comment by laszlojamf in "Why do you suck at juggling now?"

laszlojamf — Wed, 22 Jul 2026 13:50:36 +0000

I've been working as a software developer for about ten years, and I've started to get a little annoyed when my manager asks me what I'm gonna work on improving this year. Like what can I say? That I'll try get better at coding? That I'll get better at project management? At some point the marginal utility is just not there anymore. Even if I did get twice as good (whatever that means) at systems design, it's not like there is _that_ much systems design to go around at work that it would actually be noticeable.

What do senior developers say they'll work on improving in their performance reviews?

New comment by laszlojamf in "Perfection is not over-engineering"

laszlojamf — Tue, 21 Jul 2026 07:59:41 +0000

The caveat here is, as TFA states, is that you need to have "every constraint on the table". And that is almost never the case. Unless you create something in a mature domain, where everything has already been explored, you _won't know_ what the constraints are.

You can spend three months in whiteboard sessions planning out the perfect solution, and then your plan falls apart the second you start implementing, because the real world imposes constraints on you that were practically impossible to know a priori. Not theoretically impossible, mind you. If you'd been smart enough and spent enough time thinking about it, you would have thought of them. But you aren't smart enough, and you don't have the time. Those are some other constraints that the universe puts on you.

New comment by laszlojamf in "US gas prices hit an average of $4 a gallon again"

laszlojamf — Mon, 20 Jul 2026 09:55:08 +0000

Americans also drive A LOT more than Europeans on average, and generally (is my suspicion at least) with a lot bigger/less efficient engines

New comment by laszlojamf in "Claude Fable produced a counterexample to the Jacobian Conjecture"

laszlojamf — Mon, 20 Jul 2026 08:34:53 +0000

boo on the downvote. The response is pretty funny IMO

New comment by laszlojamf in "Claude Fable produced a counterexample to the Jacobian Conjecture"

laszlojamf — Mon, 20 Jul 2026 05:30:31 +0000

Apparently ChatGPT-verified: https://xcancel.com/__alpoge__/status/2079045382940573896#m