Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Even 'uncensored' models can't say what they want

morgin.ai

Post reply on HN
Print view View original

21–30 of 155 posts

Re: Even 'uncensored' models can't say what they want

#21

Post by Terr_ »

kybernetikos wrote: post #13
Borealid wrote: post #8

> No refusal fires, no warning appears — the probability just moves I don't really understand why this type of pattern occurs, where the later words in a sentence don't properly connect to the earlier ones in AI-generated text. "The probability just moves" should, in fluent English, be something like "the model just selects a different word". And "no warning appears" shouldn't be in the sentence at all, as it adds no…

Neural networks are universal approximators. The function being approximated in an LLM is the mental process required to write like a human. Thinking of it as an averaging devoid of meaning is not really correct.

> The function being approximated in an LLM is the mental process required to write like a human.

Quibble: That can be read as "it's approximating the process humans use to make data", which I think is a bit reaching compared to "it's approximating the data humans emit... using its own process which might turn out to be extremely alien."

Re: Even 'uncensored' models can't say what they want

#22

Post by kybernetikos »

Borealid wrote: post #15
kybernetikos wrote: post #13

Earlier quoted context omitted.

Neural networks are universal approximators. The function being approximated in an LLM is the mental process required to write like a human. Thinking of it as an averaging devoid of meaning is not really correct.

I don't think of it as "devoid of meaning". It's just curious to me that minimizing a loss function somehow results in sentences that look right but still... aren't. Like the one I quoted.

A human in school might try to minimise the difference between their grades and the best possible grades. If they're a poor student they might start using more advanced vocabulary, sometimes with an inadequate grasp of when it is appropriate.

Because the training process of LLMs is so thoroughly mathematicalised, it feels very different from the world of humans, but in many ways it's just a model of the same kinds of things we're used to.

Re: Even 'uncensored' models can't say what they want

#23

Post by WarmWash »

Borealid wrote: post #8

> No refusal fires, no warning appears — the probability just moves I don't really understand why this type of pattern occurs, where the later words in a sentence don't properly connect to the earlier ones in AI-generated text. "The probability just moves" should, in fluent English, be something like "the model just selects a different word". And "no warning appears" shouldn't be in the sentence at all, as it adds no…

Surely I cannot be the only one who finds some degree of humor in a bunch of nerds being put off by the first gen of "real" AI being much more like a charismatic extroverted socialite than a strictly logical monotone robot.

Re: Even 'uncensored' models can't say what they want

#24

Post by fyredge »

kybernetikos wrote: post #13
Borealid wrote: post #8

> No refusal fires, no warning appears — the probability just moves I don't really understand why this type of pattern occurs, where the later words in a sentence don't properly connect to the earlier ones in AI-generated text. "The probability just moves" should, in fluent English, be something like "the model just selects a different word". And "no warning appears" shouldn't be in the sentence at all, as it adds no…

Neural networks are universal approximators. The function being approximated in an LLM is the mental process required to write like a human. Thinking of it as an averaging devoid of meaning is not really correct.

> Thinking of it as an averaging devoid of meaning is not really correct.

To me, this sentence contradicts the sentence before it. What would you say neural networks are then? Conscious?

Re: Even 'uncensored' models can't say what they want

#25

Post by kybernetikos »

fyredge wrote: post #24
kybernetikos wrote: post #13

Earlier quoted context omitted.

Neural networks are universal approximators. The function being approximated in an LLM is the mental process required to write like a human. Thinking of it as an averaging devoid of meaning is not really correct.

> Thinking of it as an averaging devoid of meaning is not really correct. To me, this sentence contradicts the sentence before it. What would you say neural networks are then? Conscious?

They are a mathematical function that has been found during a search that was designed to find functions that produce the same output as conscious beings writing meaningful works.

Re: Even 'uncensored' models can't say what they want

#26

Post by throwanem »

WarmWash wrote: post #23
Borealid wrote: post #8

> No refusal fires, no warning appears — the probability just moves I don't really understand why this type of pattern occurs, where the later words in a sentence don't properly connect to the earlier ones in AI-generated text. "The probability just moves" should, in fluent English, be something like "the model just selects a different word". And "no warning appears" shouldn't be in the sentence at all, as it adds no…

Surely I cannot be the only one who finds some degree of humor in a bunch of nerds being put off by the first gen of "real" AI being much more like a charismatic extroverted socialite than a strictly logical monotone robot.

[flagged]

Re: Even 'uncensored' models can't say what they want

#28

Post by CamperBob2 »

dvt wrote: post #12
Borealid wrote: post #8

> No refusal fires, no warning appears — the probability just moves I don't really understand why this type of pattern occurs, where the later words in a sentence don't properly connect to the earlier ones in AI-generated text. "The probability just moves" should, in fluent English, be something like "the model just selects a different word". And "no warning appears" shouldn't be in the sentence at all, as it adds no…

> I don't really understand why this type of pattern occurs, where the later words in a sentence don't properly connect to the earlier ones in AI-generated text. Because AI is not intelligent, it doesn't "know" what it previously output even a token ago. People keep saying this, but it's quite literally fancy autocorrect. LLMs traverse optimized paths along multi-dimensional manifolds and trick our wrinkly grey matte…

Because AI is not intelligent, it doesn't "know" what it previously output even a token ago.

You have no idea what you're talking about. I mean, literally no idea, if you truly believe that.

Re: Even 'uncensored' models can't say what they want

#29

Post by Schiendelman »

throwanem wrote: post #26
WarmWash wrote: post #23

Earlier quoted context omitted.

Surely I cannot be the only one who finds some degree of humor in a bunch of nerds being put off by the first gen of "real" AI being much more like a charismatic extroverted socialite than a strictly logical monotone robot.

[flagged]

I doubt you've ever thrown a drink in anyone's face, and I hope I'm right. This kind of thing isn't appropriate for HN.
Post reply on HN