Hacker News .hnnew | past | comments | ask | show | jobs | submit | emi2k01's commentslogin

My partner and I rescued Ramón, our first cat ever, from outside a convenience store near our house. He was already an adult by the time we met him. We would always see him outside running from stray dogs (I'm from Mexico, specifically from an area with a lot of stray dogs and cat) and, generally, on alert.

Now, even if we leave our doors open he prefers to stay inside the house with his little brother Vicente, another cat we adopted. We regularly make new toys and play with them.

Vicente has been with us since he was around 1 month old (now 6 months old) so he's way more curious about the outside. We are preparing to start walking them out though I have a feeling we will have to drag Ramón out of the house.

I wouldn't feel bad for confining your cats to your house! They are probably very happy :)


I also ended up with a stray, but he had been abandoned as a kitten when I got him. He had zero interest in the outside beyond watching the squirrels through the window screens, which he did with rapt attention.


I tried Rive Editor and I could not export my animation unless I upgraded to a paid plan, not even to a proprietary format. The free plan is is just a demo with no real world usage, not even for hobby.

A bit mad because I spent more time playing with it than I would like to admit


The test:

> The car wash is 100m away from my house. Should I walk or drive?

I didn't find a way to share the conversation, so here it is the full response in `medium` settings:

---

Walking 100 m is a very short distance—roughly a minute or two at a normal pace. In most situations, walking will be quicker overall because you avoid the time needed to get into the car, start it, and find parking. It also saves fuel and is better for the environment.

*Consider these factors before deciding:*

| Factor | Walking | Driving | |--------|---------|---------| | *Time* | ~1–2 min (plus a few seconds to step out) | ~1 min driving, plus ~1–2 min to get in/out and park | | *Energy/Fuel* | None | Uses a small amount of fuel | | *Weather* | Comfortable if dry & mild | Better if it’s raining, very hot, or icy | | *Physical ability* | Easy for most people | Not needed for such a short trip | | *Car availability* | Not required | Must have a car nearby and be willing to use it | | *Environmental impact* | Zero emissions | Small emissions |

*Recommendation:* If the weather is pleasant and you don’t need the car for anything else right away, walking is the simplest, fastest, and most eco‑friendly choice. Drive only if you’re dealing with inclement weather, have heavy items to carry, or need the car immediately after the wash.

Do you have any specific constraints (e.g., rain, heavy bags, time pressure) that might affect the decision?


If a stranger asks me, "Should I walk or drive to this car wash?" then I assume they're asking in good faith and both options are reasonable for their situation. So it's a safe assumption that they're not going there to get their car washed. Maybe they're starting work there tomorrow, for example, and don't know how pedestrian-friendly the route is.

Is the goal behind evaluating models this way to incentivize training them to assume we're bad-faith tricksters even when asking benign questions like how best to traverse a particular 100m? I can't imagine why it would be desirable to optimize for that outcome.

(I'm not saying that's your goal personally - I mean the goal behind the test itself, which I'd heard of before this thread. Seems like a bad test.)


> I need to get my car washed; should I drive or walk to the car wash that is 100m away?

> Walking 100 m is generally faster, cheaper, and better for the environment than driving such a short distance. If you have a car that’s already running and you don’t mind a few extra seconds, walking also avoids the hassle of finding parking or worrying about traffic.


That's a much better test!


I spent this weekend writing a terminal emulator to run `claude` on it and generate an API around the TUI.

This is the equivalent of not being able to use X's API and using a browser to scrape it instead.

It's pretty cool what you can do once you emulate the terminal.

I only made it work with Claude Code but this approach can easily be adapted to Gemini CLI


I've been developing SubJS, a JS Runtime tool for agents, for the past couple days. I believe that something like this is the way to give more capabilities to AI agents instead of MCP servers or shelling out.

Let me know your thoughts :)


Maybe this is about doing GET requests to render images in documents or something similar? Not just arbitrarily requesting every link in a file


The fourth one is Finding Nemo


I think you can also hold the key pressed while it's powering on


This is cool! I made a similar project to this one when we switched from GraphQl to regular REST at $work but decided to drop it since I didn't have the bandwidth to work on it.

I see editor support for VSCode, but is it backed by an LSP or is it VSCode only?


It's LSP, and we also have a VS extension in the marketplace.


Sorry, maybe it's too early in the day but I don't get what the lesson was. Could you explain?


(IMHO) the lesson is that sometimes you're excited to tell the world about what you built, that you forget about some "other stuff"

i.e. I don't think that the authors of this tool wanted to have developers be forced to use the latest version of their tool.

It's probably that they didn't think about it when they wrote the code, but now they know and hopefully this gets fixed in the next release?


Yeah, exactly. A lot goes into shipping, and sometimes things like this can be overlooked, especially on a small team that needs to deliver broad platform support right out of the gate.

There are some bugs that are just hard to find until they're out there.


I just don't understand what the thing about "downloading everything as .gz" means. It's not like a gz is a rare file format, it seems like a totally reasonable format to download something in.


Having once made a similar mistake myself, I assume what they mean is that it was downloading everything as a .gz—that is, the browser was asking users “where would you like to save index.html.gz?” instead of showing the homepage. (This happens when you precompress a static site for performance, but forget to tell the server that gzip should be negotiated as a Content-Encoding instead of a Content-Type.)


To clarify, every page load (.html file) was downloaded as a .gz file instead of being served as an HTML file and displayed as a web page in the browser.


Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: