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.

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?

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.

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.

So far I’ve found most of what I’ve been looking for on www.exlibris.ch, though www.orellfuessli.ch seems quite nice as well. Normally it says in the details whether or not a particular book comes with DRM.

The DRM-free books are still digitally marked - Ex Libris will include your e-mail address in one of the first pages, and there are probably subtle differences in the text itself. I don’t mind that, though I blame the technology for the occasional annoying ‘typo’ in the book.

I ue Epubor Ultimate because I never got Calibre’s de-DRM working on my machine. It’s drag&drop for Adobe Digital Editions and also works very well in the very rare cases that I want a book that’s only available on Amazon (though buying one of those still leaves a bit of a bad taste in my mouth).
A DRM-free copy of the original is still preferred though. There’s one online shop in Switzerland that has started selling more of these lately. Maybe that’s a good sign.

I should probably care about this way more than I do, but this is a fight I’ve largely given up. The ‘right’ thing to do would be to boycott all DRM-encumbered content, but that’s a fight that very few people outside of a comparatively small circle of tech idealists would even about, much less care… and boycotts have never worked for CDs, DVDs or even VHS tapes. The sad truth is that DRM does work as designed for the overwhelming majority of less tech-savvy consumers who either aren’t aware of or can’t be bothered to try alternatives.

The good news is that it’s relatively easy to remove the DRM from ebooks, especially compared to other types of media. As long as this remains possible with just a few additional mouse clicks, the status quo “works for me”. I’m all for paying the artist/author, I just don’t want the thing I’ve bought taken away from me as soon as the publisher decides to pull the plug on their DRM server.

And what I’ve noticed here in Switzerland, even though it’s non-representative and anecdotal evidence, is that more and more ebooks are sold DRM-free.

It’s as if iPhones were only able to make calls to other iPhones

Don’t give them ideas!

Especially with the fake “eye” it creates for you on the front of the device.

I can totally see a fringe use case for meetings etc. where you can look super attentive while daydreaming or sleeping.

I’m well aware of the difference (see my other posts). But it still means that even with the maximum fine, a revenue of 100 billion is still a revenue of 96 billion. Even with an unrealistically low profit margin of 10% it was still worth it to them.

You’re making good points and I think we’re on the same page. I agree that revenue does not equal profit, I just want the fines to be as high as possible.

I don’t know, a percentage of revenue hurts more than the same percentage of net profit. Maybe some companies need to be forced to operate at a net loss until they clean up their act.

The EU knows fines of ‘up to’ 4% of revenue for privacy violations, which means the company still gets to keep 96% of whatever it’s made by breaking the law. The fine should be a minimum of 50%, plus jail time for the managers responsible. Any punishment that does not make the shareholders cry with fury is too low and will do nothing to change the situation.

IMHO the full title should read, “Hertz replaces shoddily built and expensive-to-fix cars, which just happen to be EVs, with more reliable models, which happen to be ICE cars.”

That, and there was something about charging infrastructure.

Sadly it didn’t work for me. I liked the concept but gave up after two weeks because I didn’t enjoy the experience at all and didn’t seem to make any progress (Swiss learning Spanish). YMMV of course.

TL;DR: Meta has been tracking your every move on the web for years and probably won’t be stopping anytime soon. Now they’ve announced a feature to share the information they’re collecting with you.