Hacker News: ipnon

New comment by ipnon in "Claude Fable 5.1 and Claude Mythos 5.1"

ipnon — Wed, 02 Sep 2026 02:08:55 +0000

Fable is much more expensive both in time and tokens for a marginal increase in productivity.

New comment by ipnon in "vLLM v0.28.0"

ipnon — Sat, 29 Aug 2026 23:17:57 +0000

Yes, I think this project is a good example of how complex domains aren't simply solvable just by pointing ever more intelligence at the system, even when the code is all open source and the issues are all well defined. I say this as a contributor!

New comment by ipnon in "Aspirational Clownmaxxing and Joey's cadillac todo list"

ipnon — Sat, 29 Aug 2026 00:10:16 +0000

I used to find internet slang very piercing and illuminating. I felt I was able to describe certain things which were difficult or impossible to convey with AFK language. But now that this way of speaking has become normalized outside of the internet, I find it’s lost this piercing quality, and just makes me confused. If only this cloud in the sky would move away!

New comment by ipnon in "Starbase, LA"

ipnon — Wed, 26 Aug 2026 01:22:32 +0000

From 1990 to 2025, the number of people in extreme poverty dropped from around 2.3 billion to roughly 831 million. I think we're making fast enough progress here to warrant public companies going to space on their own dime and volition.

New comment by ipnon in "How Universities Should Prepare Founders"

ipnon — Tue, 25 Aug 2026 06:57:49 +0000

I don't think there's much value in college anymore outside of as a class signifier, and most schools are signifying that you are not in the right social class.

New comment by ipnon in "Why does Opus 5 feel worse to work with?"

ipnon — Fri, 14 Aug 2026 23:28:38 +0000

Very surprised no one has this answer: because it is fundamentally not a human being.

New comment by ipnon in "Codex Security"

ipnon — Sun, 02 Aug 2026 05:36:38 +0000

I actually don't read any code! For generation I use simulations to ensure satisfactory error rates, for deterministic code I use test suites, and for user interfaces I use good ol' intuition! So I guess you could say I just write extra code that makes reading the code unnecessary. I find it quite strange to be honest! But this is the most effective way for me to ship now.

New comment by ipnon in "Ten advances in mathematics and theoretical computer science"

ipnon — Sat, 01 Aug 2026 09:36:26 +0000

But why can’t we prompt the LLM “just do math research”? This is what I don’t understand.

New comment by ipnon in "Codex Security"

ipnon — Wed, 29 Jul 2026 00:52:42 +0000

Yes, now that humans write less than 99% of code, the most important criteria for a language isn't readability, which I'd argue was always Python's main selling point, but the underlying runtime. There are practical limits to how fast a Python program can run either under I/O or CPU bound compared to other popular and mature languages with extensive libraries, like Elixir, Go or C++, depending on your use case.

New comment by ipnon in "Elixir-lang.org has a new design"

ipnon — Sat, 18 Jul 2026 23:14:07 +0000

It's a good joke but most of my applications are I/O bound. So I use Elixir for performance.

AppleScript (2006) [pdf]

ipnon — Wed, 15 Jul 2026 20:09:01 +0000

Article URL: https://www.cs.utexas.edu/~wcook/Drafts/2006/ashopl.pdf

Comments URL: https://news.ycombinator.com/item?id=48926422

Points: 8

# Comments: 0

New comment by ipnon in "AI 2040: Plan A"

ipnon — Thu, 09 Jul 2026 17:35:01 +0000

Kind of feels like fusion power at this point, always just around the corner.

New comment by ipnon in "Ask HN: Are most corporate SWE jobs performative?"

ipnon — Wed, 10 Jun 2026 14:05:25 +0000

A company is like a bridge. The job of a bridge is to support the weight of what crosses it. But if a particular deck or arch or beam or joint or bearing fails to do its own job, the bridge can fail and will catastrophically. Perhaps some beams hold more weights than others, but can any bridge be composed entirely of decks or entirely of arches or entirely of beams? Perhaps, but we do not see many of them. It is always possible to innovate in the design of bridges, but if most of the great bridges in the world all have a mix of decks and arches and beams and joints and bearings, instead of simply being composed of solely beams or solely joints, then we might begin to wonder if this composition is not accidental to the proper functioning of a great bridge, but essential to it, even if we are not particularly interested in or proficient in the Art of Being Another Part of the Whole.

A Declaration of the Independence of Cyberspace (1996)

ipnon — Sun, 07 Jun 2026 03:46:05 +0000

Article URL: https://www.eff.org/cyberspace-independence

Comments URL: https://news.ycombinator.com/item?id=48431566

Points: 2

# Comments: 0

New comment by ipnon in "Pentagon raised threat of Israeli spying on U.S. to highest level, sources say"

ipnon — Sun, 07 Jun 2026 03:21:56 +0000

I think this is correct. There has been bipartisan support of Israel for decades. Netanyahu even mentions in his autobiography that Israeli politicians usually underestimate the strength and durability of the relationship with America.

New comment by ipnon in "What I've Learned (So Far) Building Online Mini Games with Elixir and Swift"

ipnon — Wed, 27 May 2026 02:03:45 +0000

I’ve never thought about how the room model matches the LiveView socket model before. Which socket library are you using?

New comment by ipnon in "A look at Denver’s “Unlocking Housing Choices” plan"

ipnon — Tue, 12 May 2026 02:19:12 +0000

My neighborhood in California added plenty of these and it didn’t change the vibe of the neighborhood at all. It’s a great YIMBY solution because it satisfies both the pro and anti development crowds.

What's a mathematician to do? (2010)

ipnon — Sun, 10 May 2026 11:26:50 +0000

Article URL: https://mathoverflow.net/questions/43690/whats-a-mathematician-to-do

Comments URL: https://news.ycombinator.com/item?id=48083007

Points: 179

# Comments: 86

Mathematics Genealogy Project

ipnon — Fri, 08 May 2026 08:55:43 +0000

Article URL: https://www.mathgenealogy.org

Comments URL: https://news.ycombinator.com/item?id=48060490

Points: 1

# Comments: 0

New comment by ipnon in "A Theory of Deep Learning"

ipnon — Thu, 07 May 2026 01:12:36 +0000

A real theory would predict phenomena thus far unseen. We already know about this 4 part taxonomy.