Hacker News: yayitswei

New comment by yayitswei in "OpenCV 5 Is Here: The Biggest Leap in Years for Computer Vision"

yayitswei — Tue, 09 Jun 2026 16:17:26 +0000

Try a coding agent for writing and tuning the OpenCV part, and have it explain its choices. That's probably the most practical path to shipping a working system.

Speaking from experience: never used OpenCV before, recently vibe coded a tool that makes supercuts of pool videos, trimming each clip from the cue ball's first strike to when the motion stops.

New comment by yayitswei in "The 29th International Obfuscated C Code Contest (IOCCC) 2025 Winners"

yayitswei — Sun, 07 Jun 2026 07:36:32 +0000

In case anyone was wondering, the IOCCC specifically permits LLM use in their guidelines.

"The IOCCC has a rich history of remarkable winning entries created by authors who skillfully employed various techniques (often their own tools) to develop their code."

New comment by yayitswei in "Leave Me Behind"

yayitswei — Mon, 25 May 2026 15:10:15 +0000

What if you could finish your passion project in an evening? Would that increase not the time, but capacity for deep exploring and side projects?

New comment by yayitswei in "How diamonds are made"

yayitswei — Sun, 17 May 2026 15:18:30 +0000

Expensive because they were perceived as rare. Classic article: https://priceonomics.com/diamonds-are-bullshit/

Synthetic has pretty much eaten their lunch now.

New comment by yayitswei in "England Runestones"

yayitswei — Sat, 16 May 2026 16:22:55 +0000

I noticed that Futhark the programming language is also on the front page.

New comment by yayitswei in "Game: Print Gallery Of An Artist, A brief exploration of recursive spaces"

yayitswei — Wed, 15 Apr 2026 05:06:09 +0000

Loved it.

New comment by yayitswei in "Jimi Hendrix was a systems engineer"

yayitswei — Wed, 25 Feb 2026 20:48:57 +0000

This is one of the few articles where I noticed a bunch of LLM-isms and still read to the end because it was interesting.

New comment by yayitswei in "Sub-$200 Lidar could reshuffle auto sensor economics"

yayitswei — Mon, 23 Feb 2026 18:03:24 +0000

I think of Tesla autopilot as sophisticated cruise control. Can perform most driving tasks better than I can, saves a lot of cognitive work, still needs close of my 100% attention.

/Deslop

yayitswei — Thu, 19 Feb 2026 09:45:47 +0000

Article URL: https://tahigichigi.substack.com/p/12-red-flags-of-ai-writing-and-how

Comments URL: https://news.ycombinator.com/item?id=47071937

Points: 28

# Comments: 45

New comment by yayitswei in ""Token anxiety", a slot machine by any other name"

yayitswei — Tue, 17 Feb 2026 14:20:09 +0000

How ironic that agents were supposed to free us from labor, but instead they're ushering in 996 culture.

New comment by yayitswei in "I started programming when I was 7. I'm 50 now and the thing I loved has changed"

yayitswei — Tue, 10 Feb 2026 16:35:19 +0000

Is there some magic lost also when using AI to write your blog post?

New comment by yayitswei in "Prism"

yayitswei — Wed, 28 Jan 2026 15:39:24 +0000

Fwiw I was going to make the same comment about the naming, but you beat me to it.

New comment by yayitswei in "Show HN: Bible translated using LLMs from source Greek and Hebrew"

yayitswei — Thu, 22 Jan 2026 19:26:44 +0000

What's up with these?

Genesis 1:13, Eve optimal Replace 'Then' with 'And' in optimal ('And the LORD God said') and poetic_daily to preserve narrative vav-consecutive connective consistently.

New comment by yayitswei in "It's hard to justify Tahoe icons"

yayitswei — Mon, 05 Jan 2026 21:13:11 +0000

Love Tonsky's articles. My favorite is about centering things: https://tonsky.me/blog/centering/

He has a knack for putting words to the vague frustrations I feel but can't quite articulate. How does he find so many perfect examples that nail exactly what's wrong?

New comment by yayitswei in "Fighting Fire with Fire: Scalable Oral Exams"

yayitswei — Sat, 03 Jan 2026 19:19:15 +0000

Tried it in earnest. Definitely detect some aggression, and would feel stressed if this were an exam setting. I think it was pg who said that any stress you add in an interview situation is just noise, and dilutes the signal.

Also, given that there's so many ways for LLMs to go off the rails (it just gave me the student id I was supposed to say, for example), it feels a bit unprofessional to be using this to administer real exams.

New comment by yayitswei in "Pg_ClickHouse: A Postgres extension for querying ClickHouse"

yayitswei — Sat, 13 Dec 2025 06:15:33 +0000

That was my first impression as well.

New comment by yayitswei in "Learning music with Strudel"

yayitswei — Tue, 02 Dec 2025 17:26:47 +0000

Looks like the theme changes are part of the arrangement (see lines 135-149).

New comment by yayitswei in "Agent design is still hard"

yayitswei — Sun, 23 Nov 2025 07:14:59 +0000

I'm cash flow positive on my SMS sales agent, it serves just one client and my revenue is at least 3x the cost of inference/hosting.

Imo the key is to serve one use case really well rather than overgeneralize.

Agent-o-rama: build, trace, evaluate, and monitor LLM agents in Java or Clojure

yayitswei — Mon, 03 Nov 2025 18:16:43 +0000

Article URL: https://blog.redplanetlabs.com/2025/11/03/introducing-agent-o-rama-build-trace-evaluate-and-monitor-stateful-llm-agents-in-java-or-clojure/

Comments URL: https://news.ycombinator.com/item?id=45802290

Points: 80

# Comments: 5

New comment by yayitswei in "My Impressions of the MacBook Pro M4"

yayitswei — Sat, 01 Nov 2025 15:12:35 +0000

Some of those, like horses, are 1% hobbies. But many of the others can be done very affordably. Buying used equipment, learning from YouTube and online resources, starting small and scaling gradually make most of those hobbies accessible at a fraction of the cost.