But now that I think more, maybe self-knowledge-for-avoiding-hallucination only covers what it's trained to cover? Maybe there really is a "reflections on trusting trust" angle here. Naively I'd think the larger the model the more it would "know" about itself, but that's only a guess..

Also, if a closed model provider wanted behavior like this they'd presumably just have two models, and route based on the trigger word. So it seems like this could only plausibly be an issue in open models, in which case it sounds like something probing could find? (eventually if not today)

E.g. "hashi" famously can mean bridge/edge/chopsticks depending on accent, but which accent has which meaning is different in Tokyo vs Osaka.

Kind of humorously, groups sometimes develop lingo to avoid all this. E.g. the JP words for science and chemistry both have the standard pronunciation "kagaku", so people in industries where both terms are used often use nonstandard pronunciations (bakegaku for chemistry).

Also the homophones thing is probably lesser of the things I mentioned. A typical sentence might only have 1 or 2 overloaded words, but it will have lots of substrings that can be parsed multiple ways.

So at a minimum, dropping kanji would mean the language needed to develop a system for where spaces go (which is less trivial than it sounds IMO). But also it would need to abandon a lot of homophones or find some way to disambiguate them. It could happen I guess, but I'm not sure how it could happen gradually.

First sentence of https://en.wikipedia.org/wiki/Remigration :

    Remigration is a far-right concept referring to the ethnic cleansing via
    mass deportation of non-white minority populations, especially immigrants
    and sometimes including native-born citizens, to their place of racial ancestry.

Like, the current thing in the news cycle is a poll that young people are now more worried than hopeful about AI. Which sounds scary, but my first thought is that one could find similar polls from the 80s and 90s about satanic cults or alien abduction..

So companies scanning books already know they'll be sued, successfully, if they don't destroy the originals. So they destroy the originals.

(The CEO doing the testing wasn't Japanese though - maybe Russian at a guess.)

I walk in, and the CEO's secretary hands me an IQ test and says I have one hour. I do the test, then I meet the CEO and we chat about general topics while she grades the test nearby. Then she announces my IQ, and the CEO says "hmm, yes, that's above the minimum I'd consider for a developer." Then for the last few minutes he goes through the 2-3 questions I got wrong and asks me to explain why I gave the answer I did.

That was the first and only interview, and about six weeks later they call me back in and the CEO made an offer. I reply that I'll need a few days to consider. CEO: "What? Why??"

The story was basically a police detective uncovering ritual cult activity by immigrants (from some unspecified place) in a NY slum. And the narrator (the detective) goes on and on about these strange foreigners and their dark skin, weird languages, heathen religions, etc.

But it only occurred to me after finishing that, though the reader is told from the start that weird cult stuff will ensue, the detective doesn't actually find anything nefarious until pretty late in the story. So with the story's timeline it's mostly just a cop being suspicious of foreigners for being foreign, until many months later he suddenly discovers unspeakable horrors of etc. etc.

The point stands either way, reread my comment. When you ask a question on SO and somebody posts a regular answer, you the asker decide whether they've answered your question/solved your problem/Xed your Y/whatever else. Until you accept it as correct, SO assumes the posted answer did not X your Y.

In contrast when random people flag your question as a dupe, they the random people decide that the other question Xes your Y. If they misread your question, tough luck, SO assumes they are correct even though you're the only one who actually knows. That's the point I was making.

> This fundamentally can't be measured.

Again, reread my comments. If SO let other people suggest that an existing question Xes your Y, and gave you a button to accept their suggestion, then SO would know roughly how often dupe flags are correct.

The point is who decides. If you ask a question and I flag it as a dupe, I might think the answers on the other question apply to yours, but only you know whether they solved your problem or not.

> I've no idea if the rate of bad duplicates is so much higher than I observed,

Sure, and neither does SO! They didn't even measure it. They only looked at the signal "does somebody with points think these questions are similar", and discarded the signal of whether the new user got any value out of the site, and I think that's what did them in.