Hacker News: jdauriemma

New comment by jdauriemma in "Ask HN: Any interesting traffic patterns in your llms.txt?"

jdauriemma — Thu, 19 Mar 2026 19:36:39 +0000

I have seen something similar in a site I work on

Ask HN: Any interesting traffic patterns in your llms.txt?

jdauriemma — Thu, 19 Mar 2026 19:23:09 +0000

For those of you deploying llms.txt in your site root, have you seen any surprising traffic patterns?

Comments URL: https://news.ycombinator.com/item?id=47444533

Points: 3

# Comments: 4

You're all staff engineers now

jdauriemma — Tue, 17 Mar 2026 19:16:30 +0000

Article URL: https://jdauriemma.com/programming/youre-all-staff-engineers-now

Comments URL: https://news.ycombinator.com/item?id=47416932

Points: 2

# Comments: 0

New comment by jdauriemma in "ATMs didn't kill bank teller jobs, but the iPhone did"

jdauriemma — Thu, 12 Mar 2026 18:51:21 +0000

+1, this is my use case as well

New comment by jdauriemma in "RFC 454545 – Human Em Dash Standard"

jdauriemma — Wed, 11 Mar 2026 17:09:02 +0000

The RFC is a joke, if you couldn't tell. Those are quotes from the text :)

New comment by jdauriemma in "RFC 454545 – Human Em Dash Standard"

jdauriemma — Wed, 11 Mar 2026 16:39:18 +0000

Next time you post a HN comment, try audibly sighing or pausing for 137 milliseconds first?

RFC 454545 – Human Em Dash Standard

jdauriemma — Tue, 10 Mar 2026 14:37:55 +0000

Article URL: https://gist.github.com/bignimbus/a75cc9d703abf0b21a57c0d21a79e2be

Comments URL: https://news.ycombinator.com/item?id=47323891

Points: 134

# Comments: 126

I want Artificial Competence, not more Artificial Intelligence

jdauriemma — Mon, 09 Mar 2026 16:29:04 +0000

Article URL: https://jdauriemma.com/programming/i-want-artificial-competence-not-more-ai

Comments URL: https://news.ycombinator.com/item?id=47311249

Points: 3

# Comments: 0

New comment by jdauriemma in "No right to relicense this project"

jdauriemma — Thu, 05 Mar 2026 17:32:37 +0000

> "Training" an LLM ist not the same as training a human being. It a metaphor. Its confusing the save icon with an actual floppy disk.

Maybe? But the design of the floppy disk is for data storage and retrieval per se. It can't give you your bits in a novel order like an LLM does (by design). From what I can tell in this case, the output is significantly differentiated from the source code.

New comment by jdauriemma in "No right to relicense this project"

jdauriemma — Thu, 05 Mar 2026 15:08:13 +0000

This is interesting and I'm not sure what to make of it. Devil's advocate: the person operating the AI also was "trained with the code," is that materially different from them writing it by hand vs. assisted by an LLM? Honestly asking, I hadn't considered this angle before.

New comment by jdauriemma in "Show HN: Clocksimulator.com – A minimalist, distraction-free analog clock"

jdauriemma — Wed, 25 Feb 2026 14:27:49 +0000

Better than 90% of the slop that gets ladled into the front page, bravo. The world needs more Clock Simulator-like projects.

New comment by jdauriemma in "Global Intelligence Crisis"

jdauriemma — Mon, 23 Feb 2026 00:36:34 +0000

It’s AI booster fanfic, but it’s well-written so kudos. The charts are slop though.

I want Artificial Competence, not more Artificial Intelligence

jdauriemma — Sat, 21 Feb 2026 19:08:25 +0000

Article URL: https://jdauriemma.com/programming/i-want-artificial-competence-not-more-ai

Comments URL: https://news.ycombinator.com/item?id=47103672

Points: 3

# Comments: 0

New comment by jdauriemma in "Single vaccine could protect against all coughs, colds and flus"

jdauriemma — Fri, 20 Feb 2026 00:45:28 +0000

This team is at Stanford, unless I’m reading the article incorrectly. Still awful that the US pulled out of WHO.

New comment by jdauriemma in "After two years of vibecoding, I'm back to writing by hand"

jdauriemma — Mon, 26 Jan 2026 14:54:03 +0000

That's the sad part. Empiricism is scarce when people and companies are incentivized to treat their AI practices as trade secrets. It's fundamentally distinct from prior software movements which were largely underwritten by open, accessible, and permissively-licensed technologies.

New comment by jdauriemma in "Ask HN: Do you have any evidence that agentic coding works?"

jdauriemma — Wed, 21 Jan 2026 11:38:31 +0000

Can you update the title? "Do you have any evidence that agentic coding works?" sounds like you're seeking verifiable data, but in your post you're soliciting advice for how to use these tools. I clicked hoping for empiricism and got the same hamster wheel of "you're holding it wrong" that I see in every social media comment section about AI tooling.

Software ate the world; what's AI going to do to software?

jdauriemma — Thu, 15 Jan 2026 17:49:45 +0000

Article URL: https://jdauriemma.com/misc/software-ate-the-world-whats-ai-going-to-do-to-software

Comments URL: https://news.ycombinator.com/item?id=46636374

Points: 2

# Comments: 1

New comment by jdauriemma in "Show HN: WebTiles – create a tiny 250x250 website with neighbors around you"

jdauriemma — Thu, 15 Jan 2026 16:45:51 +0000

Heads up: I clicked a tile and got the hamsterdance music pretty loud in my ears. Serves me right for being distracted during a meeting but still, sound warning :)

New comment by jdauriemma in "25 Years of Wikipedia"

jdauriemma — Thu, 15 Jan 2026 15:58:53 +0000

Example?

New comment by jdauriemma in "LLM Problems Observed in Humans"

jdauriemma — Wed, 07 Jan 2026 18:26:11 +0000

The big difference is accountability. An LLM has no mortality; it has no use for fear, no embodied concept of reputation, no persistent values. Everything is ephemera. But they are useful! More useful than humans in some scenarios! So there's that. But when I consider the purpose of conversation, utility is only one consideration among many.