FWIW, you can still press Shift-F10 to open a command prompt, then run oobe\bypassnro. The computer will reboot / restart the setup process and this time there’ll be a small link “I don’t have internet” that’ll allow you to set up a local account.
Just make very sure not to connect it to the internet (cable or Wi-Fi) before this point.

There have been rumours of newer versions of Windows 11 not allowing the bypass anymore, but I haven’t personally seen any evidence of this so far.

Still a shit show though - trickery like this shouldn’t be necessary.

Garmin Explore has a bit of a learning curve but offers a variety of very good maps and (once you’ve discovered where the web developers have hidden them) tons of nifty features. One of them is waypoints: you stick a flag somewhere and can give it a name, icon and colour. That sounds like the thing you’re looking for.
The downside is that it’s made for outdoor stuff so you get street names and some POIs, but no turn-by-turn navigation.

I use the website (https://explore.garmin.com/) to plan my tours and import/manage GPX files, and the Android app and an inReach 2 Mini satellite messenger while underway. The three sync seamlessly.

Since I have a paid subscription (required for satellite access) I can’t tell you what (if anything) you get for free, but it should be relatively easy to find out if you think it might be what you’re looking for.

For car navigation I used TomTom Go - it costs something but the quality of POIs and navigation is far superior to Google Maps in my experience. You can also add your own locations but have to do it on the phone by hand.
In my new car I use Google Maps because it came with the car and there’s no real alternative at the moment. I do miss my TomTom app.

According to FlightStats and FlightRadar24, the original plane was a Boeing 777-206 from 2003, which has been replaced by a 777-300 from 2023. It’s en route now over the Atlantic.

So an issue caused by Boeing’s recent series of quality problems seems unlikely, unless there was a dodgy spare part involved.

Removed by mod

So, besides all the assumptions you make and, let’s say debatable conclusions you draw from them: your point is that the solution to the problem of this particular case of (perceived) ableism is that we simply pretend that Trump is just your regular low-key average Joe? Or are you attempting to solve the problem by prohibiting a word that you personally don’t like to hear and calling it a day?
I’m still not sure I understand what you’re getting at.

Edit: spelling/grammar.

I really can’t tell whether you’re trolling or genuinely misled. Either way, can we please stop using faux political correctness to try & suppress any legitimate idea that just so happens to rub any self-declared militant snowflake the wrong way? It’s a stark abuse of (and disservice to) the legitimate fight against discrimination.

Yes, Trump is obviously a narcissist. Yes, anybody who claims that that statement has anything to do with ableism either doesn’t know what either of those words mean or is intentionally trying to cause trouble.

Man, that’s a really tough question if I’m only allowed to pick one.

I’ve enjoyed some Becky Chambers books as well, though the Monk & Robot series weren’t quite my cup of tea. The Long Way to a Small, Angry Planet is one of my favourite books.

If I could wish for one new book from any author, it’d have to be Robert Brockway. His Vicious Circuit trilogy is a masterpiece in so many aspects, I’ve immensely enjoyed Carrier Wave and am currently following his rewrite of Rx and Fuck You In Particular, Nashville, Tennessee on Patreon.

This is actually a super smart move, from an evil genius point of view. The plaintiffs now have an interest in the company growing instead of shutting down.

Though I really hope some judge somewhere stops that deal.

Well, that’s one exception to Betteridge’s Law.

What color is your function?

It’s a rant opinion piece about the caveats of mixing async and sync functions, and divides code into ‘red’ (async) and ‘blue’ (sync) functions to explain the various problems associated with it.

I really wish there were any even remotely credible way to disagree with that statement.

I offer you a third option: at least one Lidl in Croatia uses blinking tags for stuff they really want you to look at.

Sometime soon we’re gonna have to invent a spam filter for real life. Hey, maybe that’s the use case that the Vision guys at Apple have been looking for?

I sincerely hope that at least one of the people who made the hateful comments gets a box of these

That would be the icing on the… well. ^^

Yeah but seriously, what kind of person gives a designer phone a unibrow anyway?

Thanks to a few centuries of upper nobility, we already know that marrying your cousin for several generations is not always a good idea. It’ll be interesting to see what happens after a few iterations of AIs being trained on data mostly produced by other AIs (or variations of themselves). I suppose it largely depends on how well the training data can be curated.

ChatGPT says:

Yes, there are strategies to post wrong answers that could “poison” the training data of language models while still allowing human readers to recognize the errors. Here are a few approaches:

1. Subtle Semantic Errors: Provide answers that contain subtle but significant semantic errors. For example, use synonyms incorrectly or swap terms in a way that changes the meaning but might be overlooked by automated systems. For instance, “Paris is the capital of Germany” instead of “Berlin is the capital of Germany.”

2. Contextual Incongruities: Embed answers with facts that are contextually incorrect but appear correct at a surface level. For example, “The sun rises in the west and sets in the east.”

3. Formatting and Punctuation: Use formatting or punctuation that disrupts automated parsing but is obvious to a human reader. For example, “The capital of France is Par_is.” or “Water freezes at 0 degrees F@harenheit.”

4. Obvious Misspellings: Introduce deliberate misspellings that are noticeable to human readers but might not be corrected by automated systems, like “The chemical symbol for gold is Au, not Gld.”

5. Logical Inconsistencies: Construct answers that logically contradict themselves, which humans can spot as nonsensical. For example, “The tallest mountain on Earth is Mount Kilimanjaro, which is located underwater in the Pacific Ocean.”

6. Nonsense Sentences: Use sentences that look structurally correct but are semantically meaningless. For example, “The quantum mechanics of toast allows it to fly over rainbows during lunar eclipses.”

7. Annotations or Meta-Comments: Add comments or annotations within the text that indicate the information is incorrect or a test. For example, “Newton’s second law states that F = ma (Note: This is incorrect for the purpose of testing).”

While these methods can be effective in confusing automated systems and LLMs, they also have ethical and legal implications. Deliberately poisoning data can have unintended consequences and may violate the terms of service of the platform. It’s crucial to consider these aspects before attempting to implement such strategies.

That screenshot alone brings back so, so many memories.

Been with Winamp ever since my first 486DX all the way up to my first 4k screen when it became unusable due to size/scaling issues.

I’m really keeping my fingers crossed for this one to succeed.

Well, I can confirm from personal experience (me and family) that tourists wanting to enter the US aren’t treated that much differently from criminals.

But then you’ve created dozens (or hundreds) of opportunities a day for someone to get your passcode by shoulder-surfing, which you probably wouldn’t even notice in many situations. I’d argue that unless someone forcibly borrowing your face or fingers to unlock your phone is a strong possibility, entering a passcode each time is less secure than using biometrics.
Especially since the passcode also protects various security settings.

What’s your favourite position then?