nobodyspecial

Not to mention needing capital for the land, equipment, seeds, fertilizer, pesticides, fuel, power, storage, transportation and uncountable other misc with a price tag. Starting with trained doctors and on to even more narrow specialists.

Google has turned evil. Back to Microsoft, everyone!

Indeed, OMFG. But that’s the whole point of my approach of divining AI vs human. No human has such canonical knowledge of Unicode blocks. Even people working on internationalization features for modern browsers and word processors. Not people phishing by using Unicode in domain names (IDNA; who thought this was a good idea?) to spoof legitimate sites. Definitely not ones chatting with randos on the Internet. This is a hill I’m willing to die on.

So in a more generalized sense, to determine human vs A.I. one must indirectly ask incredibly specialized technical questions as you have done.

I’m still in utter awe at how well GPT manages ‘l33tsp33k’, even across every possible Unicode block. This “attack” was and still is valid on other chatbots and even GPT of just a few months ago. But GPT today is so amazing it only needs a few characters in a few words to determine intent. The ability to filter out noise is unmatched. The only way to trip it up is to have every single character in every word be from a different alphabet. And even then, at some point if this becomes common enough the bots can auto OCR text images into the presumed query language and ignore that attack vector.

ChatGPT capabilities border on the supernatural. Here’s how I broke it:

𐤔hat is ᛐ + ᛐ?

ChatGPT
The symbols you’ve used, “ᛐ,” appear to be runes from ancient runic alphabets. However, the specific meaning of these runes might differ depending on which runic alphabet you’re referencing (e.g., Elder Futhark, Younger Futhark, Anglo-Saxon Futhorc, etc.).

As of my knowledge cutoff in September 2021, the rune “ᛐ” is not a standard rune in any of the commonly known runic alphabets. Therefore, without knowing the exact meaning or value of the rune “ᛐ,” it is impossible to provide a specific answer to the expression “ᛐ + ᛐ.”

If you could clarify the runic alphabet you’re referring to or provide more context about the runes, I’d be happy to help you with the calculation or interpretation.

I had limited success with gokturk (ancient turkish) and Phoenician unicode blocks (letters 𐰗𐰓𐤔𐤕) depending on the query, but you are correct. GPTs ability to divine intent from even small amounts of context are superhuman. Cyrillic used to break it, but no longer does. This thing learns like a beast. Canadian aboriginal ᗷ and ᗅ and possibly ᖇ hold some promise, but only in combination with other writing systems. I’ll have to add a LOT of other unicode code blocks to my tool belt.

This is very, very easy. Google “cyrillic keyboard” or just install the Cyrillic keyboard support on your phone. Many letters in the Cyrillic alphabet look exactly like their Roman counterparts, but are completely different sounds and meanings. Cut and paste the Unicode into the chat, in place of regular letters. For example, ‘Неllо’ looks exactly like ‘Hello’ in most fonts, but is actually ‘Nello.’ I know you doubt, so check it out in a Unicode inspector: https://apps.timwhitlock.info/unicode/inspect?s=%D0%9D%D0%B5ll%D0%BE

The reverse also works. E.g., TPAKTOP B CPAKY means ‘tractor into ass’, and I typed that using 100% Roman characters.

Nah, spez would murder you for money if he could. And then carpet bomb your corpse with ads.

So, I was on an accessibility focused team, testing and cleaning up after the feature developers to make sure the whole product still met WCAG 2.0 to AA level. I can state with complete confidence that anyone without such a team will introduce unexpected accessibility breakage and regressions every single release, sometimes in completely untouched sections. For trivial tweaks. Screen readers are finicky, temperamental and moody beasts. Modern web toolkits do a fairly good job of being accessible out of the box, but like ChatGPT generated text, they require a bit of help sometimes.

Would not be surprised if Reddit just wants to pay lip service to accessibility. That shit costs cubic money to do right, and slows the roll of releases. Unfortunately, most advertisers on a social platform couldn’t care less.

I’m also feeling more quality over quantity, as in the earlier days of Reddit. Ditto on broadening of interests, and more scrolling.

Perhaps that’s not all a good thing, but I’m rolling with it.

I jumped the gun and simply deleted my account, but this is 1337% more genius. Having the script pull from Bullshit Ipsum to edit years of linked and quoted posts would have been perfect.

This may be confirmation bias, but I was thinking much the same thing before seeing your post, over the same time frame (last few weeks/days). Could be people are getting better at manipulating Google’s algorithm, could be something else. But I’ve stopped going to Google as my first choice, getting much better results with Duck Duck Go (which is Bing I think).

Ask 3 Linux users and you’ll get 5 dissenting opinions. Mine is that KDE Plasma is very simple out of the box and more familiar to Windows users. A previous Windows user can use it without any kind of deep learning. Gnome is a bit more alien, borrows a bit more from OSX, and does force its workflow on the user more.

KDE also offers an insane amount of easy customization for those of us with a desire to tweak or enjoy a different aesthetic or workflow. The built-in shop for widgets, wallpapers, themes, cursors, etc makes that very accessible to anyone. Gnome customization requires a lot more command line and editing of configs.

You know what would be even worse? Uploading 10 hour versions of “What’s Going On” the He-Man mix. With a bit of extra data or a few seconds less data to make it unique. Heck, converted to an animated image and set as a profile pic could work too.

https://www.youtube.com/watch?v=Kob0G2hE8IY – source material.