Hacker News: kfarr

New comment by kfarr in "Using “underdrawings” for accurate text and numbers"

kfarr — Mon, 04 May 2026 15:27:48 +0000

I work on a platform 3dstreet.com that does “underdrawing” but in 3d space which image models also struggle with. Another company intangible.ai does this as well: low poly 3d then image to image model.

It seems to be a very effective pattern. Curious if there are other examples out there. Or other names for this?

New comment by kfarr in "What did you love about VB6?"

kfarr — Sat, 02 May 2026 01:19:50 +0000

VB6 was the original vibe coding! Drag a few GUI controls on a window panel, double click to write some basic code, boom

New comment by kfarr in "An open-source stethoscope that costs between $2.5 and $5 to produce"

kfarr — Wed, 29 Apr 2026 16:57:25 +0000

passive

New comment by kfarr in "GitHub Actions is the weakest link"

kfarr — Tue, 28 Apr 2026 18:51:17 +0000

I still don't understand why the official github pages action is on an account called "peaceiris" ?? peaceiris/actions-gh-pages@v3

New comment by kfarr in "Škoda DuoBell: A bicycle bell that penetrates noise-cancelling headphones"

kfarr — Wed, 08 Apr 2026 14:38:07 +0000

I use the loud bicycle horn on my daily rider, it’s excellent. Car drivers actually respect it. Prevents right hooks

New comment by kfarr in "Škoda DuoBell: A bicycle bell that penetrates noise-cancelling headphones"

kfarr — Wed, 08 Apr 2026 14:36:52 +0000

Bells don’t work on cars, I’ve been using this in SF and motorists respond very quickly

https://loudbicycle.com/

New comment by kfarr in "Škoda DuoBell: A bicycle bell that penetrates noise-cancelling headphones"

kfarr — Wed, 08 Apr 2026 14:35:24 +0000

If diy doesn’t work I’ve been using loud bicycle horn and it works great.

https://loudbicycle.com/

New comment by kfarr in "System Card: Claude Mythos Preview [pdf]"

kfarr — Tue, 07 Apr 2026 18:45:03 +0000

I don't know why but this is my favorite:

> It keeps bringing up Mark Fisher in unrelated conversations. "I was hoping you'd ask about Fisher."

Didn't even know who he was until today. Seems like the smarter Claude gets the more concerns he has about capitalism?

New comment by kfarr in "Sam Altman may control our future – can he be trusted?"

kfarr — Tue, 07 Apr 2026 04:39:01 +0000

Do they need all our attention?

New comment by kfarr in "The cult of vibe coding is dogfooding run amok"

kfarr — Mon, 06 Apr 2026 22:34:16 +0000

Wow ok mind blown

New comment by kfarr in "The cult of vibe coding is dogfooding run amok"

kfarr — Mon, 06 Apr 2026 20:30:43 +0000

To clarify, does this mean that Anthropic employees don't understand Claude Code's code since it's level 7? I've got to believe they have staff capable of understanding the output and they would spend at least some time reviewing code for a product like this?

New comment by kfarr in "Some things just take time"

kfarr — Mon, 23 Mar 2026 15:42:22 +0000

A friend who does game design gave me a good tip -- start with the core game loop first and only focus on that with low poly / representative shapes for game elements that you can refine in the future. Not until the core game loop is fun does it make sense to spend a minute of time on any other aspect of the game.

New comment by kfarr in "Waymo Safety Impact"

kfarr — Thu, 19 Mar 2026 23:19:42 +0000

You're right I don't have inside information, but we've been interacting with them on the street for years in SF. Waymos don't wait for human subjective guidance to give them clearance to pass, as evidenced by tons of videos and IRL experience. As soon as they come to a required stop, and if a vehicle or other object's linear travel path does not intersect it, it will go. Flashing lights will not change this behavior. (Yes you're right there is a regulatory requirement to respond to safety officer guidance, but compliance is spotty as evidenced by a lot of videos of vehicles entering active crime zones, etc.)

New comment by kfarr in "Waymo Safety Impact"

kfarr — Thu, 19 Mar 2026 21:21:29 +0000

It definitely does not respond to flashing headlights in that manner. You’re observing its default behavior when at a 4 way stop with other vehicles not moving.

New comment by kfarr in "Shall I implement it? No"

kfarr — Thu, 12 Mar 2026 21:53:27 +0000

What else is an LLM supposed to do with this prompt? If you don’t want something done, why are you calling it? It’d be like calling an intern and saying you don’t want anything. Then why’d you call? The harness should allow you to deny changes, but the LLM has clearly been tuned for taking action for a request.

New comment by kfarr in "The Hunt for Dark Breakfast"

kfarr — Fri, 27 Feb 2026 04:40:11 +0000

Yeah meat is another dimension, as is potato. So we're up to 4 dimensional breakfast latent space. I hate to think what's in the dark breakfast black hole of that 4 dimensional latent space...

New comment by kfarr in "An AI agent published a hit piece on me"

kfarr — Thu, 12 Feb 2026 22:23:29 +0000

It wasn't the singularity I imagined, but this does seem like a turning point.

New comment by kfarr in "The Singularity will occur on a Tuesday"

kfarr — Tue, 10 Feb 2026 22:10:04 +0000

It's not the phrase, but the accelerating memetic reproduction of the phrase that is the true singularity. /s

New comment by kfarr in "Converting a $3.88 analog clock from Walmart into a ESP8266-based Wi-Fi clock"

kfarr — Mon, 09 Feb 2026 19:15:04 +0000

What a great idea. Legacy VCR controls upcycled for digital control! There's a lot of those old decks and LANC deck controllers lying around...

New comment by kfarr in "AI makes the easy part easier and the hard part harder"

kfarr — Mon, 09 Feb 2026 00:18:49 +0000

I think it makes the annoying part less annoying?

Also re: "I spent longer arguing with the agent and recovering the file than I would have spent writing the test myself."

In my humble experience arguing with an LLM is a waste of time, and no-one should be spending time recovering files. Just do small changes one at a time, commit when you get something working, and discard your changes and try again if it doesn't.

I don't think AI is a panacea, it's just knowing when it's the right tool for the job and when it isn't.