Hacker News: jryan49

New comment by jryan49 in "Ask HN: AI productivity gains – do you fire devs or build better products?"

jryan49 — Thu, 26 Mar 2026 05:50:38 +0000

AI output is non-deterministic right? Can both of you be right? Maybe it gets it right sometimes, and doesn't other times.

New comment by jryan49 in "Ask HN: How do you offload all coding to AI?"

jryan49 — Wed, 25 Mar 2026 12:36:20 +0000

When people say they don't write the code, they mean they don't type it, but if there are not vibe coding garbage they are still watching what the agent outputs, and redirects it when it goes wrong. Instead of fixing the code manually they prompt the LLM.

New comment by jryan49 in "Show HN: Primer – build software with AI agents one milestone at a time"

jryan49 — Mon, 23 Mar 2026 19:26:23 +0000

Have you seen openspec, or any of the others in this space?

New comment by jryan49 in "Reports of code's death are greatly exaggerated"

jryan49 — Sun, 22 Mar 2026 20:15:38 +0000

Yes... maybe not 99%...

New comment by jryan49 in "How do you plan to make a living after AI takes your job?"

jryan49 — Mon, 02 Mar 2026 16:23:07 +0000

IMHO no one know what the heck is going to happen. Probably will have to adapt to the situation as needed... In other words, it's too hard to predict to come up with a plan ahead of time?

New comment by jryan49 in "Iran's Ayatollah Ali Khamenei is killed in Israeli strike, ending 36-year rule"

jryan49 — Sat, 28 Feb 2026 23:01:09 +0000

Cause people are sick of their tax money going to endless wars

New comment by jryan49 in "The United States and Israel have launched a major attack on Iran"

jryan49 — Sat, 28 Feb 2026 15:26:18 +0000

lol we all hope

New comment by jryan49 in "Fed's Cook says AI triggering big changes, sees possible unemployment rise"

jryan49 — Wed, 25 Feb 2026 01:04:24 +0000

Save up enough money to be safe for many years after I get laid off so I have plenty of time to figure out what to do.

New comment by jryan49 in "Claws are now a new layer on top of LLM agents"

jryan49 — Sat, 21 Feb 2026 14:30:24 +0000

I mean we know at this point it's not super intelligent AGI yet, so I guess we don't care.

New comment by jryan49 in "DOGE Track"

jryan49 — Thu, 19 Feb 2026 13:42:49 +0000

So we should all go out and get arrested and put and jail to solve nothing. Sounds like a plan...

New comment by jryan49 in "America's $1T AI Gamble"

jryan49 — Wed, 11 Feb 2026 00:45:56 +0000

Works great in other countries with high unemployment. That's exactly what happens! People elect a person who says they are going to change everything to fix it and they never get around to it for some reason :)

Just look at the mess south America is in...

New comment by jryan49 in "America's $1T AI Gamble"

jryan49 — Tue, 10 Feb 2026 15:51:14 +0000

I love how they say with a straight face that when AI takes over they will finally share all the fruits of capital with us.

New comment by jryan49 in "Eight more months of agents"

jryan49 — Tue, 10 Feb 2026 13:49:28 +0000

Someone will package up all that intuition and skills and I imagine people won't have to do any of these things in future.

New comment by jryan49 in "Ask HN: Non AI-obsessed tech forums"

jryan49 — Tue, 10 Feb 2026 01:23:26 +0000

https://cyberspace.online/

New comment by jryan49 in "xAI joins SpaceX"

jryan49 — Mon, 02 Feb 2026 23:36:15 +0000

How can you clearly believe anything Musk says at this point. It's not 'clear' at all what he actually believes and what he just makes up.

New comment by jryan49 in "Ask HN: How do you force yourself to take breaks while coding?"

jryan49 — Mon, 02 Feb 2026 16:30:13 +0000

Work on something you don't want to be working on. :)

New comment by jryan49 in "Automatic Programming"

jryan49 — Mon, 02 Feb 2026 03:52:36 +0000

Then why was Claude code generating exact copies of code files all with the copyrights intact last week when I used it?

New comment by jryan49 in "Software Survival 3.0"

jryan49 — Fri, 30 Jan 2026 23:07:02 +0000

I wish people would stop up voting AI Nostradamus articles...

New comment by jryan49 in "Show HN: I'm building an AI-proof writing tool. How would you defeat it?"

jryan49 — Thu, 29 Jan 2026 21:53:30 +0000

I only switched tab/windows once (to input the question). So I'm not sure how severely you'd want to rate that. The webcam doing eye tracking might help if the person isn't good a typing and can copy one side without checking if the other is okay...

New comment by jryan49 in "AGENTS.md outperforms skills in our agent evals"

jryan49 — Thu, 29 Jan 2026 21:48:35 +0000

Something that I always wonder with each blog post comparing different types of prompt engineering is did they run it once, or multiple times? LLMs are not consistent for the same task. I imagine they realize this of course, but I never get enough details of the testing methodology.