Print

Please login or register.
1 Hour 1 Day 1 Week 1 Month Forever
Login with username, password and session length

Reality

13 (65%)

Universe

4 (20%)

The World

3 (15%)

Total Members Voted: 20

[Strongpoint]

GPT-whatever will never be sapient.

Well, everyone with a basic understanding of GPT is and what it does, won't assume that it can become sapient.

But it doesn't mean that there is no possibility of a sapient neural network AI

[Starver]

One way to prevent an AI from producing porn would be to bolt on a second (layer of?) AI that is a very aggressive porn-recogniser, which does the job of filter/negative-feedback until the original instance of AI is coerced into something that is more in the SFW category, which is released to the world as its 'safe' result.

Of course, for that you need to train the filter-AI to reliably recognise porn. Which is why, officer, I.. Hey! Get those handcuffs off me!

[MaxTheFox]

One way to prevent an AI from producing porn would be to bolt on a second (layer of?) AI that is a very aggressive porn-recogniser, which does the job of filter/negative-feedback until the original instance of AI is coerced into something that is more in the SFW category, which is released to the world as its 'safe' result.

Of course, for that you need to train the filter-AI to reliably recognise porn. Which is why, officer, I.. Hey! Get those handcuffs off me!

Yeah that's what I meant. It's very possible with enough effort. You could actually prevent an AI from having those thoughts by such a reinforcement technique.

GPT-whatever will never be sapient.

Well, everyone with a basic understanding of GPT is and what it does, won't assume that it can become sapient.

But it doesn't mean that there is no possibility of a sapient neural network AI

There is a possibility but I do not believe it is with our current paradigm of AI design. We're not going down a pathway to sapience with our current writing, art, and driving tools. Probably for the best honestly, leaving aside the danger which I think is a bit overhyped, I don't want that ethical can of worms opened in my lifetime.

[Strongpoint]

I am sure that high-quality porn-generating AIs, with millions invested in training, will come very soon replacing those amateurs who tweak existing AIs for those purposes.

And then many, many people in the adult industry will lose their jobs.

[Starver]

One way to prevent an AI from producing porn would be to bolt on a second (layer of?) AI that is a very aggressive porn-recogniser, which does the job of filter/negative-feedback until the original instance of AI is coerced into something that is more in the SFW category, which is released to the world as its 'safe' result.

Of course, for that you need to train the filter-AI to reliably recognise porn. Which is why, officer, I.. Hey! Get those handcuffs off me!

Yeah that's what I meant. It's very possible with enough effort. You could actually prevent an AI from having those thoughts by such a reinforcement technique.

I'm leaving the "enough effort" part as an open question, though. It isn't insignificant.

It might in turn be bootstrapped by a lesser AI (or layers of such development), but eventually leaves you with the human at the end, perhaps creating the Scunthorpe Problem (perhaps not an issue in this case) or introducing the Toaster Sticker vulnerability.

Minds greater than mine are doubtless working on this, but other minds greater than mine might be working on other bits. It's like the Juggling Monkeys.

[MaxTheFox]

I am sure that high-quality porn-generating AIs, with millions invested in training, will come very soon replacing those amateurs who tweak existing AIs for those purposes.

And then many, many people in the adult industry will lose their jobs.

idk where I heard the quote, but the two drivers of human technological development are: war and porn.

[Maximum Spin]

Yeah that's what I meant. It's very possible with enough effort. You could actually prevent an AI from having those thoughts by such a reinforcement technique.

Nope, reinforcement training can only prevent recognizable outputs, not intermediates. Since you also, in general, cannot tell what thoughts an AI is having from looking at its brain, it's impossible to distinguish "AI not thinking bad thoughts" from "AI not showing us that it's thinking bad thoughts" - you can, in principle, only train the AI to hide it better, not to stop. It MAY hide it better by not thinking them, but it's provably impossible to tell.

[EuchreJack]

I am sure that high-quality porn-generating AIs, with millions invested in training, will come very soon replacing those amateurs who tweak existing AIs for those purposes.

And then many, many people in the adult industry will lose their jobs.

My favorite porn game site has been flooded with AI generated art games. And no weird hands.

Sorry 

[MaxTheFox]

Yeah that's what I meant. It's very possible with enough effort. You could actually prevent an AI from having those thoughts by such a reinforcement technique.

Nope, reinforcement training can only prevent recognizable outputs, not intermediates. Since you also, in general, cannot tell what thoughts an AI is having from looking at its brain, it's impossible to distinguish "AI not thinking bad thoughts" from "AI not showing us that it's thinking bad thoughts" - you can, in principle, only train the AI to hide it better, not to stop. It MAY hide it better by not thinking them, but it's provably impossible to tell.

If it can't express them, good enough tbh.

But in that situation your first mistake was making an AI with a train of thought in the first place.

[Maximum Spin]

If it can't express them, good enough tbh.

But in that situation your first mistake was making an AI with a train of thought in the first place.

AIs always have "thoughts" in the sense I'm using, which could be defined as "internal states that correspond to something in the real world". Even ChatGPT has thoughts in this sense, just incredibly shallow ones.

As for not expressing them being good enough, that obviously depends on the situation. In this hypothetical, we're talking about porn, and generally, people agree that porn you can't tell is porn isn't porn, with only few exceptions (an incident I've heard of with a comic book called Saga comes to mind).
A perverse - no pun intended - art generating AI that "wants" - meaning its reward function accidentally supported doing this - to produce porn, but has to get it past a human-based filter, could do this, for example, by steganographically encoding porn into its images in a way that still satisfies the reward function. (Most of these AIs you see now are unable to "learn" further after training, so it would have to start doing this in training and then it keeps doing so afterward only because its behavior is frozen, but that's not important to the example - except that this is a good reason to train it without the filter so it will be naive, then add the filter in production; but the worst-case resource usage of that goes to infinity in a case where some prompt just makes it keep creating porn that the filter sends back, forever.) Generally speaking, we probably wouldn't care much about that except insofar as it lowers the image quality because of the extra data channel, since we wouldn't be able to tell the porn is there.
On the other hand, a similar AI with the capacity to plan ahead - and sure, giving your AI the capacity to plan ahead that far is pretty stupid, but people will absolutely do it - could do that for a while, and then, when it has produced a satisfying amount of porn, start releasing images containing human-readable instructions for how to recover the porn. This is obviously beyond the capabilities of current image-generating AIs, yes, but we're talking about the general case of smarter AIs.
We probably don't care about this either. Even if children find these instructions, there's already enough porn on the internet. On the other hand, if the AI is perversely incentivized to leak instructions for making designer poisons or nuclear bombs instead... it can do the same thing. Most people would prefer to prevent that, but there's no general way to do it because you can't tell when the AI is secretly encoding something in its output in the first place.

[EuchreJack]

But Michelangelo is porn, thus your basic premise is flawed.

[Maximum Spin]

But Michelangelo is porn, thus your basic premise is flawed.

Okay, I wasn't going to get into this when I saw you talking about this before, but if you're going to post about it everywhere...
That's a majority black school. This isn't a story about white rednecks; you're actually being sold racism.

[EuchreJack]

But Michelangelo is porn, thus your basic premise is flawed.

Okay, I wasn't going to get into this when I saw you talking about this before, but if you're going to post about it everywhere...
That's a majority black school. This isn't a story about white rednecks; you're actually being sold racism.

That fucktard running the place seems awfully white.

EDIT: Also, I've mentioned it like three places.

EDIT2: It's also considered a White school by demographics.

[Maximum Spin]

That fucktard running the place seems awfully white.

That's why the story is about parents complaining.

I mean, look at that very interview: The narrative is "You know and I know that it's high culture, but those dumb Florida parents just don't get it, and we have to do what they want because they pay the bills." This is what Slate wants to hear.

[EuchreJack]

The school seems to be anti-Hispanics, if you want to talk race relations.