Hacker News: KolenCh

New comment by KolenCh in "Mathematicians aren't mourning their craft: Translating "After Math" for SE"

KolenCh — Sun, 13 Sep 2026 17:38:32 +0000

Software engineers have learnt to read the reaction to coding agents as a split between people who love the craft and people who care about the product. Seen through that lens, mathematicians upset about OpenAI’s Navier–Stokes result look like craft-lovers in denial, moving the goalposts. I think that misreads them. “After Math”, by Silvia De Toffoli and Eamon Duede, argues that mathematics was never after the answer: the understanding is the product. Then I extrapolate to research software, where I’d argue the same holds for code that establishes scientific results.

Mathematicians aren't mourning their craft: Translating "After Math" for SE

KolenCh — Sun, 13 Sep 2026 17:38:32 +0000

Article URL: https://blog.kolen.dev/math/after-math

Comments URL: https://news.ycombinator.com/item?id=49686453

Points: 2

# Comments: 1

New comment by KolenCh in "Progressive disclosure for mathematical proofs: The parallel with cybersecurity"

KolenCh — Sat, 12 Sep 2026 22:02:27 +0000

My previous submission covers the Navier–Stokes “incident” itself. Here I want to look at a parallel: AI agents are finding security bugs and producing mathematical proofs faster than the people working in these fields can absorb them.

Can mathematics borrow from coordinated vulnerability disclosure? I’d propose a registry that records work as it develops, with timestamps that others can verify, together with circles that gradually widen before public release. This would give people a record of their contribution without having to rush an unfinished proof out. But it only helps if we also give credit to ideas and partial results.

Progressive disclosure for mathematical proofs: The parallel with cybersecurity

KolenCh — Sat, 12 Sep 2026 22:02:27 +0000

Article URL: https://blog.kolen.dev/math/math-vs-cybersecurity

Comments URL: https://news.ycombinator.com/item?id=49677667

Points: 5

# Comments: 1

Unpacking the Navier–Stokes blowup: the math, the machines, & the mathematicians

KolenCh — Fri, 11 Sep 2026 18:55:55 +0000

Article URL: https://blog.kolen.dev/math/Navier-Stokes

Comments URL: https://news.ycombinator.com/item?id=49663462

Points: 1

# Comments: 0

New comment by KolenCh in "Taste Is All That's Left"

KolenCh — Fri, 07 Aug 2026 22:41:46 +0000

Have you read the article? It has an unbalanced emdash: `word— another word`. A novice mistake that an LLM likely will not commit nowadays. In standard typography—depending on which guide you need to follow — it can only be padded by space on both side or neither.

New comment by KolenCh in "Ask HN: What Linux distro do you daily drive?"

KolenCh — Fri, 24 Jul 2026 20:17:19 +0000

I used to distro-hop a lot and in recent years settled with RHEL. The key change over the years is how fragile the supply chain becomes, so while distro like Arch Linux is a great learning experience, I just want to put a layer of maintainers who have higher stake than others between me and the world. (RHEL has a free tier for developers limited to 16 instances.)

New comment by KolenCh in "Show HN: Boo – Screen-style terminal multiplexer built on libghostty"

KolenCh — Fri, 12 Jun 2026 09:06:09 +0000

How would this compare to shpool: https://github.com/shell-pool/shpool

New comment by KolenCh in "Claude Fable is relentlessly proactive"

KolenCh — Fri, 12 Jun 2026 08:07:34 +0000

I think it should be “Claude Fable is relentlessly protective until it isn’t” and pull more on the thread that it “hits a hidden guardrail” and drop into Opus. Both the fact that it knows and deployed such a workaround on a CSS problem and the fact that it is nowhere near cybersecurity/biology/frontier AI dev and triggered the guardrail terrifies me.

New comment by KolenCh in "Rsync: 3.4.1 –> 3.4.3"

KolenCh — Wed, 03 Jun 2026 15:38:27 +0000

rsync regression since 3.4.3

This link (edit: I link to https://github.com/NixOS/nixpkgs/pull/522245#issuecomment-45... but probably the anchor is stripped automatically?) is the clearest that I can find to point out what's the problem in a neutral tone with links to issues you can track yourself.

There is other less civic discussions around the issue that I decide not to cite.

One comment describe the situation aptly: 3.4.1 contains security bugs, later versions fixes it but contains regressions. So choose wisely.

*Apparently* both are AI related: the security bugs are probably discovered by AI. Rushing to fix lots of these results in the use of AI, which leads to regressions.

Rsync: 3.4.1 –> 3.4.3

KolenCh — Wed, 03 Jun 2026 15:38:27 +0000

Article URL: https://github.com/NixOS/nixpkgs/pull/522245

Comments URL: https://news.ycombinator.com/item?id=48385541

Points: 3

# Comments: 1

New comment by KolenCh in "Show HN: Files.md – Open-source alternative to Obsidian"

KolenCh — Tue, 19 May 2026 04:11:22 +0000

That’s not what he said. And that part is from the GTD principle, much older than the “second brain” wave. That GTD principle, backed by psychological research, is basically saying that you should extract what you have in your mind immediately when you have it / remember it, so that you don’t need to keep it in your mind all the time. That free your mind to perform at optimal capacity. In psychological lab test, they basically test people doing “remember X and perform this next task Y. I’m going to ask you about X after you finish Y.” The mere fact that you need to remember X degrades your performance.

New comment by KolenCh in "Uncle Bob: It's Over"

KolenCh — Wed, 06 May 2026 17:47:58 +0000

I experienced both kind of sessions, one kind is like very complicated thing and it finish thousands of lines on its own for quite a while (long horizon problem), another kind is like a seemingly simple task that the agent done in a minute but then I need a few back and forth to get it right easily taking me 30 minutes of my time.

The former kind of experience can make us misjudge how much time we think a task would take us (with agents) to do. And then when the second kind happens, it would be quite disrupting as now we felt like it is delaying our progress.

So tracking the time taken when the second kind happens can help us calibrating what we can expect. I mean if we’re lucky it might take us no time but then we can’t expect being lucky all the time.

New comment by KolenCh in "Uncle Bob: It's Over"

KolenCh — Mon, 04 May 2026 00:23:06 +0000

Have you tracked your time and confirmed this?

The reason I an ask is, it would felt like a 5 minutes task, but I track my time and found out often time I thought I’d just quickly check the progress made by the agents and it would easily becomes a 10, 15, or even a 30 minutes task.

New comment by KolenCh in "Changes in the system prompt between Claude Opus 4.6 and 4.7"

KolenCh — Sun, 19 Apr 2026 22:39:52 +0000

“Claude” is more specific than “you”. Why rely on attention to figure out who’s the subject? Also it is in their (people from Anthropic) believe that rule based alignment won’t work and that’s why they wrote the soul document as “something like you’d write to your child to show them how they should behave in the world” (I paraphrase). I guess system prompt should be similar in this aspect.

New comment by KolenCh in "The Oxford Comma – Why and Why Not (2024)"

KolenCh — Fri, 27 Mar 2026 15:55:19 +0000

It eliminated some ambiguity. It should be quite self evident that even without an example it is quite impossible to eliminate all ambiguity (it’s a feature of human language.) The more important property is that it never introduces more ambiguity. Ie at worst it doesn’t help, but not making it worse.

New comment by KolenCh in "AI Agents Can Autonomously Perform Experimental High Energy Physics"

KolenCh — Tue, 24 Mar 2026 10:57:59 +0000

This is uniquely interesting to me because humongous amount of data are produced in HEP so automatic research (data analysis) in that domain is I think a huge enabler. It makes trying out ideas much cheaper (in human time) and you could flag interesting results for humans to investigate further. One deal breaker is because big data is so big in HEP, current operations are already very storage and compute bound. If only we can raise trillions of dollars in HEP and perhaps join force with ESA and build a fleet of data centers in space.

AI Agents Can Autonomously Perform Experimental High Energy Physics

KolenCh — Tue, 24 Mar 2026 10:46:05 +0000

Article URL: https://arxiv.org/abs/2603.20179

Comments URL: https://news.ycombinator.com/item?id=47500797

Points: 3

# Comments: 1

New comment by KolenCh in "Tell HN: AI tools are making me lose interest in CS fundamentals"

KolenCh — Mon, 16 Mar 2026 09:52:14 +0000

My naïve answer to this is, one should never be interested in things because of how useful it might be, but because of the thing itself. Otherwise, AI won’t be the first to make one losing interest. With interest, AI may even make it more addicting. Another distinction to make is, when you use AI, are you taking a shortcut, or channeling it to automate the boring stuffs so that you can explore things you otherwise don’t have time to explore?

New comment by KolenCh in "Unauthenticated remote code execution in OpenCode"

KolenCh — Tue, 13 Jan 2026 10:43:32 +0000

I learnt this the hard way: if anyone is sending multiple emails, with seemingly very important titles and messages, and they get no reply at all, the receiver likely haven’t received your email rather than completely ghosting you. Everyone should know this, and at least try a different channel of communication before further actions, especially from those disclosing vulnerability.