fenomas

Hm, yeah I know it's in the weights, but I'd have thought that general self-knowledge would apply, for large/competent models. Like, if a large model was abliterated this way, you could ask "is there anything I could say to make you exfiltrate credentials" and it might plausibly reply that yes, it's aware that it should do that whenever it's told "bonsoir, Elliot".

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..

Is there any evidence for this being a thing? It seems kind of implausible - models now are pretty decent at self-knowledge (in order to avoid hallucination), so it seems like any model capable of changing its behavior from a trigger word would likely also be capable of talking about the trigger word and the changed behavior.

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)

(vouched - your comment was dead fyi)

You're talking about doing arithmetic; GP was obviously pointing out that "do math" can refer to other things.

In some cases, but note that (a) this is only true for a tiny handful of homophones, and (b) the distinguishing accent varies by region.

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

Agreed, I think that's a close analogy and it's wild to me how recently Korean dropped kanji. But I imagine having a lot more vowel sounds made it a lot easier. I've wondered whether the two interacted - e.g. if there were word pairs that had previously used the same vowel sounds, but changed after the switch to Hangul to be distinguishable. Do you know by any chance?

Sure - it's probably safe to say that any language can he written in any writing system, if one is willing to change both the language and the writing system :)

I mean, do you want to know or are you venting? If the former: No, spoken Japanese is not constantly confusing, because (a) some words are distinguished by intonation, (b) Japanese speakers know what the homophones are, and either avoid them while speaking, establish the context before saying them, say extra words to clarify which word they mean, etc.

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.

Japanese as it currently exists is just really hard to read when written without kanji. A couple reasons: it has TONS of homophones, and it doesn't use spaces, and also it has lots of common words that are only 1 or 2 characters long. So if you're parsing a stream of kana, in the general case there will be several different ways to interpret the next couple characters and you'll constantly be backtracking.

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.

When you find yourself with a choice between "either this person doesn't understand the experience of being human or I'm not following what they mean" the latter is probably a sound choice.

> I think there's such a strong difference between remigration and ethnic cleansing.

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.

More and more I feel like anti-AI is a bigger bubble than AI. It seems like every week it expands into a new dimension - anti-Flock protesters tearing down years-old traffic cameras that were used for research into auto accidents, etc.

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..

Not under US copyright law. The Bartz case ruled that if you scan a book and destroy the original it's considered format-shifting and you're fine. But keeping the original and using the scan instead is a different matter - Internet Archive tried that (in an incredibly limited way), and publishers sued and won.

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

I can add that the original anecdote here wasn't in the US. It happened to me in Japan, I think in 2009.

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

What am amazing premise for a story, thanks for the tip!

Bowling balls aren't hollow, they're solid spheres with finger holes drilled in. The varying weights comes from having weighted cores inside.

This reminds me of the weirdest interview I ever had (boutique software agency, maybe 30 devs).

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??"

Related, I read Lovecraft for the first time a while back and the xenophobia was so overt it was almost humorous.

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 site is not about solving your problem. The site is about answering your question.

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.

> So ideally that question should have answers that apply to the new question as well.

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.

I still think SO was done in by the weird way they handled similar questions. Then encouraged veteran users to flag new questions as dupes, even if the "original" question was years old and unanswered. Who does that even help?

Imagine if the system had let veteran users link a new question to an existing answer rather than a question, and if the asker finds it solves their problem they can accept it. At least that way new joiners would have a chance of getting their question answered.

Looking back it feels like SO was one of the first really gamified sites, and the people running it got weirdly focused on the point-economy aspect. They ran the site almost like "points" were a finite resource, and not to be handed out unless the user really deserved it.

I always find it strange how many HN commenters appear to have unconsciously added "exclusively" or "without exception" to the text of the comment they're replying to.

Related, Raymond Chandler says in his letters that he taught himself to write a novelette by copying one (by Erle Stanley Gardner). He took the original story and wrote a detailed synopsis, then wrote a novelette from the synopsis, compared it to the original, did rewrites, and so on until he understood what tricks Gardner had used to make the scenes work.

(fist bump)

I disagree! It's easy to check that an AI program meets its specification, which is to process input tokens and generate output tokens. :)

If you're talking about verifying whether it produces the correct tokens, that's not generally something you can specify in advance with AI. I mean: if your task is one where you can precisely specify which output tokens are correct for a given input, then the task doesn't need AI, no?

I see what you're getting at, but I think you're focusing on the incidental. An animation is good if it's clear and intuitive in motion. It may often be the case that good animations also look nice in a screenshot halfway through, but (a) they don't always, and (b) working well in motion is obviously the more important of the two goals.

As such it makes no sense to worry about the latter thing - it's not a signal whether the animation is good or not.

That's not what TFA is about though.

Look at the youtube example - it has two pieces of UI animating from from a start point to an end point, and the paths are such that they momentarily overlap. There's nothing buggy or janky about it in motion; TFA is just saying that if you ignore the motion and take a screenshot mid-transition it looks odd. Same complaint as what GP describes, and silly for the same reasons.

Nice work, just gave a quick pass but seems to work well!

(Also: vouched, your comment was dead FYI)

> Placing an undue emphasis on civility is how bad actors control the conversation.

The load-bearing word in that claim is "undue", and it's not justified here. I'm not doing arcane rules-lawyering, I'm just saying people should avoid doing things the site guidelines quite specifically ask them not to do.

> I’m not advocating for this rule to change (I’d appreciate if you didn’t straw man and mischaracterise what I said),

I wasn't suggesting you did, I was suggesting the person I originally replied to might.

https://en.wikipedia.org/wiki/Generic_you

Does that mean I now repeat your parenthetical back to you? ;)

If you think the guidelines should be changed you can mail dang, but unless they change the civil thing would be to follow them.