Hacker News: fourthark

New comment by fourthark in "I beg you to follow Crocker's Rules, even if you will be rude to me"

fourthark — Sat, 14 Mar 2026 14:00:05 +0000

> But if you are the kind of person who cries out against this abomination we must warn you that people who go through life expecting informal variant idioms in English to behave logically are setting themselves up for a lifetime of hurt.

New comment by fourthark in "10% of Firefox crashes are caused by bitflips"

fourthark — Fri, 06 Mar 2026 01:48:19 +0000

That's easy to ignore.

New comment by fourthark in "Claude's Cycles [pdf]"

fourthark — Wed, 04 Mar 2026 03:07:44 +0000

I think the point is that you have a better idea of what you want it to remember and even a small hint can have big impact.

Just saying "write up what you know", with no other clues, should not perform any better than generic compaction.

New comment by fourthark in "AI Made Writing Code Easier. It Made Being an Engineer Harder"

fourthark — Sun, 01 Mar 2026 16:06:40 +0000

Wish we could downvote articles. Is it legitimate to flag AI slop?

New comment by fourthark in "Show HN: Xmloxide – an agent-made Rust replacement for libxml2"

fourthark — Sun, 01 Mar 2026 01:04:11 +0000

Does it fix the security flaws that caused the original project to be shut down?

New comment by fourthark in "Show HN: Claude-File-Recovery, recover files from your ~/.claude sessions"

fourthark — Sat, 28 Feb 2026 03:56:18 +0000

Odd how this thread is a recapitulation of your experience with the LLM.

What is take from this is that it's pointless to try to find out why an LLM does something - it has no intentions. No life and no meaning, quite literally.

And if you try to dig you'll only activate other parts of its training, transcripts of people being interrogated - patients or prisoners, who knows. Scary and uncreative stuff.

New comment by fourthark in "We Will Not Be Divided"

fourthark — Sat, 28 Feb 2026 01:19:17 +0000

Most survive by bending. See e.g. Google and surveillance a decade ago.

New comment by fourthark in "The Om Programming Language"

fourthark — Thu, 26 Feb 2026 05:08:01 +0000

There have been a few.

New comment by fourthark in "You are not supposed to install OpenClaw on your personal computer"

fourthark — Tue, 24 Feb 2026 02:00:49 +0000

(Which it is?)

New comment by fourthark in "Claws are now a new layer on top of LLM agents"

fourthark — Sun, 22 Feb 2026 04:05:47 +0000

Presumably https://en.wikipedia.org/wiki/S-expression

New comment by fourthark in "How I use Claude Code: Separation of planning and execution"

fourthark — Sun, 22 Feb 2026 03:30:10 +0000

Strongly agree about the deterministic part. Even more important than a good design, the plan must not show any doubt, whether it's in the form of open questions or weasel words. 95% of the time those vague words mean I didn't think something through, and it will do something hideous in order to make the plan work

New comment by fourthark in "How I use Claude Code: Separation of planning and execution"

fourthark — Sun, 22 Feb 2026 02:04:21 +0000

This is exactly what the article is about. The tradeoff is that you have to throughly review the plans and iterate on them, which is tiring. But the LLM will write good code faster than you, if you tell it what good code is.

New comment by fourthark in "Antarctica sits above Earth's strongest 'gravity hole' – how it got that way"

fourthark — Thu, 19 Feb 2026 12:28:46 +0000

> it is weakest beneath the frozen continent of Antarctica *after accounting for Earth's rotation*.

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

fourthark — Wed, 18 Feb 2026 03:40:46 +0000

Why do you find it useless for legacy code? I find I have to give it plenty of context but it does pretty well on legacy code.

And Ask DeepWiki is a great shortcut for finding the right context… Granted this is open source and DW is free.

Is it the specific nature of your work?

New comment by fourthark in "The "AI agent hit piece" situation clarifies how dumb we are acting"

fourthark — Sat, 14 Feb 2026 02:30:25 +0000

What is your argument? There are a lot of bots, therefore humans are no longer in charge?

New comment by fourthark in "Claude’s C Compiler vs. GCC"

fourthark — Mon, 09 Feb 2026 08:07:37 +0000

But only if there is a competent compiler engineer running the AI, reviewing specs, and providing decent design goals.

Yes it will be far easier than if they did it without AI, but should we really call it “produced by AI” at that point?

New comment by fourthark in "Case study: Creative math – How AI fakes proofs"

fourthark — Mon, 26 Jan 2026 05:47:27 +0000

“This is key!”

New comment by fourthark in "Show HN: ChartGPU – WebGPU-powered charting library (1M points at 60fps)"

fourthark — Thu, 22 Jan 2026 03:08:16 +0000

Can't tell what this demo is streaming, looks like a static line but it's working hard on something. It can't seem to decide whether to display the top number in red or green either.

New comment by fourthark in "Skip is now free and open source"

fourthark — Thu, 22 Jan 2026 00:13:11 +0000

Third possibility negates the first two.

Also, did VB6 put anyone out of work?

New comment by fourthark in "Claude's new constitution"

fourthark — Wed, 21 Jan 2026 23:11:38 +0000

Maybe you have JS disabled? I see it flash from Jan 22 to Jan 21. :-)