Hacker News: pmg101

New comment by pmg101 in "Claude Fable 5.1 and Claude Mythos 5.1"

pmg101 — Wed, 02 Sep 2026 05:01:10 +0000

Or "will need fixing", right?

A society that runs on stimulants is badly broken

pmg101 — Fri, 28 Aug 2026 19:40:10 +0000

Article URL: https://www.currentaffairs.org/news/a-society-that-runs-on-stimulants-is-badly-broken

Comments URL: https://news.ycombinator.com/item?id=49483290

Points: 49

# Comments: 26

New comment by pmg101 in "ElevenLabs, TwelveLabs, ThirteenLabs"

pmg101 — Sat, 22 Aug 2026 17:02:53 +0000

Remembr when it was missng lettrs out of wrds

New comment by pmg101 in "Interviewing Engineers in the AI Era: Lessons from a Year of Rebuilding"

pmg101 — Fri, 07 Aug 2026 11:21:32 +0000

Yeah it tells you nothing of value. It's the Recency Bias taken to its ultimate conclusion isn't it. Anything I learned about AI I learned in the last few months but somehow that's as important as all the experience of my decades long software career? Come on.

New comment by pmg101 in "Taste Is All That's Left"

pmg101 — Fri, 07 Aug 2026 11:11:33 +0000

Somebody at $formerwork wrote a "skill" that takes a poorly/briefly specified Jira ticket, and "fleshes it out", purportedly so that when an agent picks up the ticket it has more context.

Really at that point, with head in hands, rather than try to explain the foolishness, I decided I was better out.

"Zoom and enhance" used to be a joke/meme, apparently it's now "engineering".

New comment by pmg101 in "I'm Scared a Stranger Will Call My Novel AI, So I Built GitHub for Words"

pmg101 — Wed, 05 Aug 2026 18:23:07 +0000

I agree.

My guess is the author either

1. Deliberately used LLM tics in their prose, for artistic and provocative reasons, or 2. Used AI

It's quite interesting to reflect on.

New comment by pmg101 in "There Will Come Soft Rains (1950) [pdf]"

pmg101 — Mon, 03 Aug 2026 23:24:53 +0000

Today is August 4, 2026

There Will Come Soft Rains (1950) [pdf]

pmg101 — Mon, 03 Aug 2026 23:24:53 +0000

Article URL: https://users.wpi.edu/~zrbutzke/Docs/BradburyStories(1).pdf

Comments URL: https://news.ycombinator.com/item?id=49162653

Points: 453

# Comments: 445

New comment by pmg101 in "Prevent cognitive debt by manually retyping LLM-generated code"

pmg101 — Mon, 03 Aug 2026 20:41:45 +0000

I'm REALLY REALLY not enjoying this current middle ground where we may be on the cusp of LLMs writing all code better than I could OR we may be on the cusp of realising that this is a chimera.

Mostly I just want to skip forward to the point where we find out which track we're on, because until we know, I feel constantly tense.

New comment by pmg101 in "More German than many Germans"

pmg101 — Mon, 03 Aug 2026 10:59:56 +0000

Meanwhile, here in the UK we had the bus with no door at all that you could just jump on and off from in moving traffic. People trusted to manage their own risk. I remember this vividly from my childhood, in the 80s and 90s, in London. Not anymore though, sadly.

https://www.ltmuseum.co.uk/blog/routemaster-design-icon

New comment by pmg101 in "AI doesn't generate working products, that's still your job"

pmg101 — Sat, 01 Aug 2026 12:59:42 +0000

Thanks. I do think I see the distinction you're making.

New comment by pmg101 in "AI doesn't generate working products, that's still your job"

pmg101 — Sat, 01 Aug 2026 12:54:18 +0000

Can you give an example of a pattern that was considered common practice in a book 10 to 15 years ago that would be considered low-quality code today?

My experience is pretty much the reverse: that we seem to just go round and round relearning the lessons that had already been learned in the past.

New comment by pmg101 in "AI doesn't generate working products, that's still your job"

pmg101 — Sat, 01 Aug 2026 12:26:34 +0000

Isn't "spaghetti code" a casual term to describe "complex and disjointed codebase"? What's the difference? Have I been using the term wrong all this time?

New comment by pmg101 in "Show HN: What should the GUI for AI agents look like?"

pmg101 — Fri, 31 Jul 2026 07:50:17 +0000

Whether or not it's a transitional phase, it seems reasonable to want and to build better tools for where we are now rather than where we may be in some unspecified future, wouldn't you say?

New comment by pmg101 in "The Religion of Speed"

pmg101 — Fri, 31 Jul 2026 07:45:11 +0000

The longer I spend in my career the more obvious this is to me. Unfortunately younger colleagues don't always have the maturity to have also realised this, which can be a problem if they end up above me in the management chain!

I try to kickstart reflection on this by saying things like "Some of the biggest impact I've had has been the code I chose not to write."

New comment by pmg101 in "The Economic Benefit of Refactoring"

pmg101 — Thu, 30 Jul 2026 15:58:53 +0000

(Just to note that although the article is on martinfowler.com Martin is not the author. It's attributed to Thoughtworks CTO Giles Edwards-Alexander.)

New comment by pmg101 in "The Economic Benefit of Refactoring"

pmg101 — Thu, 30 Jul 2026 15:56:47 +0000

It's very interesting to have some data on this.

It matches my experience which is that LLMs greatly benefit from well factored code, but are not particularly adept at creating such code.

Much like most human developers I suppose!

New comment by pmg101 in "Hamburg's Stadtpark: A Park Built to Be Used"

pmg101 — Wed, 29 Jul 2026 20:08:52 +0000

It's the "it's not X. It's Y" pattern isn't it?

Although the verb "stayed with me" seems a little sloppy to me too.

New comment by pmg101 in "Hannah Fry Wins the Leelavati Prize in 2026 for Mathematics Outreach"

pmg101 — Sat, 25 Jul 2026 06:51:43 +0000

And didn't the NHS app use Bluetooth proximity to alert you if you'd been in contact with a COVID case early in the pandemic? A nice case of life imitating art.

New comment by pmg101 in "It's getting harder to focus every day"

pmg101 — Fri, 24 Jul 2026 20:13:58 +0000

Yes, I've found it to be completely incompatible with managers and the corporate world.

I had some success in small startups where I was left to my own devices and built cool stuff whenever I felt the urge to do so.

In corporate jobs I just have to lie and describe smooth and steady daily progress while actually working in sudden fits and starts, but it's hard to maintain the lie.