kfarr

Tell me about it, I maintain an open source project in the civil engineering space and it's ... detailed.

Thanks, that's a much better example of what I was trying to explain. Again, I'm projecting humanity onto a machine, but it's not a big stretch to imagine that the interaction of attention heads over high-dimensional vectors produces "decisions" that can't be articulated in the moment, only described after the fact in text form.

Although it's a no no to anthropomorphize on HN, it's worth noting that some folks think humans are post-hoc rationalizers as well:

https://www.patheos.com/blogs/tippling/2013/11/14/post-hoc-r...

https://www.researchgate.net/publication/316045349_Post_Hoc_...

Just let go of the entire R&D team and then you have a 50% margin business.

UPDATE: Also bad news, you need to let go of all of sales and marketing and G&A. And THEN it's a 50% margin business.

Classic... want to cast to the chromecast but I'm on the wifi

Some of these are actually nice and appropriate to use in certain contexts. Also this issue is hilarious: https://github.com/vorpus/performativeUI/issues/2

> ai virus from earlier today

curious what this means...

Nor the streaming service Net Flux

Context: this is a demo of a deterministic layout calculation library https://github.com/cosmiciron/layoutmaster#dancing-text (not affiliated, I was just confused so saving you a click)

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?

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

passive

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

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

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

https://loudbicycle.com/

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

https://loudbicycle.com/

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?

Do they need all our attention?

Wow ok mind blown

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?

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.

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.)

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.

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.

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...

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

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

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...

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.

Yeah it’s not accurate at all. Not the OPs fault but the purpleair sensors are placed by users. Right now it says fidi is 9° warmer than haight. Plausible, but it could also be the only 1 sensor reporting from fidi is on a balcony near a drier vent.