Hacker News: low_tech_punk

Zero Sum Game

low_tech_punk — Sun, 08 Mar 2026 03:39:58 +0000

Article URL: https://code.chuanqisun.com/zero-sum-game/

Comments URL: https://news.ycombinator.com/item?id=47294168

Points: 1

# Comments: 0

New comment by low_tech_punk in "A CPU that runs entirely on GPU"

low_tech_punk — Wed, 04 Mar 2026 14:21:10 +0000

Saw the DOOM raycast demo at bottom of page.

Can't wait for someone to build a DOOM that runs entirely on GPU!

New comment by low_tech_punk in "Clawdbot Renames to Moltbot"

low_tech_punk — Tue, 27 Jan 2026 20:52:26 +0000

When I visit https://www.molt.bot/ with Edge browser, there is a bloody red screen screaming malware. What's wrong with the name?

Missed Connections NYC [video]

low_tech_punk — Tue, 13 Jan 2026 05:53:31 +0000

Article URL: https://www.youtube.com/shorts/anRJ_aQzfRQ

Comments URL: https://news.ycombinator.com/item?id=46597693

Points: 2

# Comments: 0

New comment by low_tech_punk in "System: Control your Mac from anywhere using natural language"

low_tech_punk — Tue, 06 Jan 2026 15:23:18 +0000

User: Hey AI, turn off my Mac

AI: (after 10 minutes of deep reasoning) Ah! I found the solution. I need to cause a power surge in the grid to power off your device.

New comment by low_tech_punk in "Show HN: Quantum Tunnel"

low_tech_punk — Sun, 04 Jan 2026 23:46:00 +0000

Google's ML team really nailed it. There are lots hand/head/eye tracking demos made with mediapipe.

I recommend checking out The Poet Engineer: https://x.com/poetengineer__

New comment by low_tech_punk in "Show HN: Ez FFmpeg – Video editing in plain English"

low_tech_punk — Sat, 27 Dec 2025 20:23:38 +0000

No AI is appealing but there is the cliff problem. If there is one small thing the mini language can't handle, the user would have no chance solving it themselves. They might as well start with an LLM solution first.

One workaround is that when there is syntax error, let user optionally switch to LLM?

New comment by low_tech_punk in "Coffee linked to slower biological ageing among those with severe mental illness"

low_tech_punk — Sun, 07 Dec 2025 01:34:41 +0000

Is it possible that the coffee drinkers have more social interaction with the barista and others? It's unclear from the paper if they eliminated the confounding factors around coffee drinking.

New comment by low_tech_punk in "Linux Kernel Explorer"

low_tech_punk — Fri, 28 Nov 2025 04:43:14 +0000

I believe the entire web app was a mod on top of monaco (vscode)? Really great hack!

New comment by low_tech_punk in "iPhone Pocket"

low_tech_punk — Tue, 11 Nov 2025 15:31:46 +0000

A slingshot, A blind fold, A pocket -- Steve Jobs never said that.

New comment by low_tech_punk in "Say Hi to Kit"

low_tech_punk — Thu, 06 Nov 2025 14:20:32 +0000

Everyone asks, what does the fox say, no one cares how the fox feels. Thank you Mozilla, now we know the fox feels like open source.

New comment by low_tech_punk in "Claude Code on the web"

low_tech_punk — Mon, 20 Oct 2025 21:21:05 +0000

IMHO, parallel tasks across multiple repos is not as useful as parallel tasks in one repo.

New comment by low_tech_punk in "Apple M5 chip"

low_tech_punk — Wed, 15 Oct 2025 14:16:46 +0000

Not all is lost: AI can still be acronym for Apple Intelligence.

New comment by low_tech_punk in "Comprehension debt: A ticking time bomb of LLM-generated code"

low_tech_punk — Tue, 30 Sep 2025 14:51:41 +0000

I had a similar thought, feature not bug.

The nature of programming might have to shift to embrace the material property of LLM. It could become a more interpretative, social, and discovery-based activity. Maybe that's what "vibe coding" would eventually become.

New comment by low_tech_punk in "Comprehension debt: A ticking time bomb of LLM-generated code"

low_tech_punk — Tue, 30 Sep 2025 14:10:02 +0000

Most programmers don't understand the low level assembly or machine code. High level language becomes the layer where human comprehension and collaboration happens.

LLM is pushing that layer towards natural language and spec-driven development. The only *big* difference is that high level programming languages are still deterministic but natural language is not.

I'm guessing we've reached an irreducible point where the amount of information needed specify the behavior of a program is nearly optimally represented in programming languages after decades of evolution. More abstraction into the natural language realm would make it lossy. And less abstraction down to the low level code would make it verbose.

New comment by low_tech_punk in "We can’t circumvent the work needed to train our minds"

low_tech_punk — Wed, 10 Sep 2025 16:51:35 +0000

This piece reminds me of another article musing on the necessity of manual memory: https://numinous.productions/ttft/#how-important-is-memory.

That article articulated the reason slightly differently, arguing you need to hold multiple concepts in your head at the same time in order to develop original ideas.

Still, I'm not sure you have to remember everything, but I agree you have to remember the foundational things at the right abstraction layer, upon which you are trying to synthesize something new.

New comment by low_tech_punk in "Eternal Struggle"

low_tech_punk — Mon, 01 Sep 2025 12:13:22 +0000

maxwell's demon peeking from the dark side

New comment by low_tech_punk in "Vibe coding the MIT course catalog"

low_tech_punk — Fri, 08 Aug 2025 18:30:00 +0000

Nice write-up!

Semi-incremental Markdown renderer for LLM

low_tech_punk — Fri, 08 Aug 2025 18:12:41 +0000

Article URL: https://github.com/chuanqisun/semidown

Comments URL: https://news.ycombinator.com/item?id=44839941

Points: 1

# Comments: 0

New comment by low_tech_punk in "GPT-5 for Developers"

low_tech_punk — Thu, 07 Aug 2025 20:27:00 +0000

I think the router applies to chatgpt app. The developer APIs expose manual control to select the specific model and level of reasoning.