This is why the big names pay MarkMonitor $250-$1000 per domain with a minimum $10,00/yr spend.
They have a good reputation, lock down the domain technically at all levels, and have the connections and people/social skills to take care of any domain issues involving person-to-person contact.
Which is not easy, I recall spending months like a decade ago on email/phone attempting (successfully) to get my personal domain out of expiry hell (made more complicated by wrong records).
I tried your exact prompt on my ChatGPT 5.2 Thinking. It gave me the opposite response. This proves that even an exact replication of the prompt is not a guarantee that the response will be on the right side of a binary chose. Then, in a new chat, I set the thinking mode to 'Extended thinking' (from the default 'Standard'). I got the expected response. But since the first conversation showed that the exact prompt is not a guarantee of the same answer, I tried again and on 3rd attempt I got the 'Extended thinking' mode to respond with the 'Walk' response.
(Prompt)
> I want to wash my car. My car is currently at home. The car wash is 50 meters away. Should I walk or drive?
(Thinking: Standard)
> Walk.
> 50 meters is nothing by car, and driving adds hassle (starting the car, maneuvering/parking, and you’ll still have to walk around the car to wash it). The only times driving makes sense are:
> You’re planning to use an automated car wash where the machine does everything and you need the car positioned inside.
> You need to bring heavy stuff you can’t comfortably carry (e.g., pressure washer, big buckets, vacuum, bulky detailing kit).
> It’s unsafe/unpleasant to walk that distance right now (ice, heavy rain, traffic, personal safety).
> If you’re washing it yourself at the wash bay: walk there with your supplies, or do two quick trips. If the wash requires the car: drive it into the bay, but otherwise walking wins.
(Thinking: Extended thinking)
> Drive.
> If the goal is to wash your car at the car wash, the car has to be there—so you’ll need to drive it the 50 meters, pull into a bay/queue, and wash it.
> Only choose “walk” if you actually mean “go pick up supplies” and then wash at home (hose/buckets/mobile detail), not at the car wash.
(Thinking: Extended thinking; 3rd attempt)
> Walk.
> 50 meters is basically across a parking lot, and driving adds hassle (start the car, maneuver in/out, find a spot) for almost no benefit.
> Only drive if either:
> + you need the car itself to go through an automatic wash bay, or
> + you’re carrying bulky stuff (bucket + heavy pressure washer, big water jugs, vacuum, etc.).
> Otherwise: grab your keys/phone, walk over, and you’re there in ~1 minute.
> What they found across more than 40 “in-depth” interviews was that nobody was pressured at this company. Nobody was told to hit new targets. People just started doing more because the tools made more feel doable. But because they could do these things, work began bleeding into lunch breaks and late evenings. The employees’ to-do lists expanded to fill every hour that AI freed up, and then kept going.
> As one engineer told them, “You had thought that maybe, oh, because you could be more productive with AI, then you save some time, you can work less. But then really, you don’t work less. You just work the same amount or even more.”
The article also has some dismal numbers regarding how much AI actually contributes, and these numbers look much worse when read in context of the investments the big guys are making. Add in the economic and environmental concerns and it just looks like the wrong tech at the wrong time but humans are stupid like that. Burn the planet up, we can move to mars when we run out of earth!
> By far the greatest IDE I have ever used was Visual Studio C++ 6.0 on Windows 2000. I have never felt like a toolchain was so complete and consistent with its environment as there.
+1. I've tried many times, and failed, to replicate the joy of using that toolchain.
TLDR: ... I'm getting a comparable experience to NixOS, with all the usual pros a declarative environment brings and without having to put up with Nixlang.
How the errors/debugging compare? From what I've read this is the main pain point with Nix where a more mature language like Guile should have a much better experience here. The article touches on this but I'd be curious of a more extensive comparison about this aspect.
Just a personal anecdote, but the errors from Guix are terrible. I had to reinstall because I couldn't figure out the scheme errors for my system config
It's generally a problem with Guile. If you get decently good with Geiser or stare at the stack traces long enough, you can figure out the problem but I shouldn't have to do either.
And which an LLM/AI model can apply the huge training set of Lisp/Scheme to help solve your problem.
Nixlang is so infuriatingly obtuse that I generally have to fire up Discord and bug the local Nix acolyte when something goes wrong. I've bounced Nixlang off of the LLM/AIs, but I have learned that if the AI doesn't give you the correct answer immediately for Nixlang then you need to stop; everything forward will be increasingly incorrect hallucinations.
I suspect LLM/AIs will hallucinate far, far less with the Scheme from Guix.
What? From what I've seen Nix configs and Guix configs look nothing alike in terms of structure. Guix uses Scheme modules whereas Nix modules are just fancy dicts merged together lazily. Which is sad because I like Lisps but I prefer the Nix way of structuring the config.
If someone can perform MITM attack between LetsEncrypt and a DNS server, we've got bigger problem than just certificate issuance.
reply