I switched recently to OpenWrt from MT, which code agents are also good at. I'd wager most issues are going to be related to the user not specifying what they want clearly enough. The translation from network concepts to RouterOS config is pretty 'fat-free', so there's not much room for hallucinations beyond syntax errors, which can be verified via the API.

These are the types of solutions we should be cheering, because people voluntarily chose the less-CO2 product due to its appeal. No heavy handed laws required.

Spending hundreds on new hw to save $20 a year in power cost.

That doesn't help, however, if users are lazy and don't unload the dishwasher after opening it to grab a clean plate or whatever.

It's a nice feature that can be added with existing sensors and one line of logic in the uC. Another one I noticed recently is garage door openers with the photo transmitter/receiver ('beam') to stop the door if someone blocks it can use that same beam to turn on the light if broken when the door is up. Handy if entering a dark garage from outside.

'Happily' is also a stretch, as they really don't have a choice if served a valid court order.

If you want encryption that is safe from the US government, keys need to be stored in your head. Anything physical is subject to court orders.

You do have to solder, though I wouldn't be surprised if one can find sata power to barrel adapters on AliExpress.

I was actually quite worried, because I've been using GHCP for large chunks of work, but the billing estimator they released shows I was only at about $150-200 a month in API priced tokens. Sure, that's a subsidy for my $20 subscription, but not insane.

Heavy use of agentic coding tools, in a responsible manner, probably lands somewhere around that $200/m mark at API pricing. Assuming that makes the provider money, I don't see that being hard to swallow for businesses employing developers in Western countries, given the hours it can save.

The real risk here is to personal project vibe coders. Building a huge app by abusing subsidized plans is ending.

Just today, when I wasn't being especially chatty with GHCP, I used about 12 requests to get a few thousand line changes in 3 projects I'm juggling. The last project repo of copilot I closed, in 3 hours burned 38M input tokens, 28M cache, and like 400K out. For GPT5.4, high. That's like $135, in half the day, 1 of 3 instances. No crazy tool use, just lots of docs and unorganized code. GHCP charged like 70 cents for that on the old plan.

It hit me that as it's deciphering some verbose log file, it has also read through all the source code that wrote that log, and likely all of the discussions/commits that went into building that (broken) feature.

Once they're in MD format, you can always get your favorite agent to do more formatting and organization, which was one of the big reasons I moved away from ON.

If you go adding any old repo to APT, you have the same risk. You should look at how much code review goes into packages for major distros like Debian, hint, not much, especially once the initial package was accepted.

GHCP at least is transparent about the pricing: hit enter on a prompt= one request. CC/Codex use some opaque quota scheme, where you never really know if a request will be 1,2,10% of your hourly max, let alone weekly max.

I've never seen much difference with context ostensibly being shorter in GHCP, all of the models (in any provider) lose the thread well before their window is full, and it seems that aggressive autocompaction is a pretty standard way to help with that, and CC/Codex do it frequently.

I only use password keys for things that need to be scripted.

I reenabled DB on that alt port when I did the recent major update, just in case, but it wasn't necessary. After the upgrade, OpenSSH was alive and ready.

Mind you, I think GHCP is a great service at an excellent price, but the hardcore vibe coders complain about the rate limits that I've never personally experienced using the CLI.

There, sorted!

I've used/use both, and find them pretty comparable, as far as the actual model backing the tool. That wasn't the case 9 months ago, but the world changes quickly.