Uncensored Models • Hacker News Board

Re: Uncensored Models

#271

Post by kgwgk » Mon, May 15, 2023, 5:04 PM UTC

SAI_Peregrinus wrote: post #114

A4ET8a8uTh0 wrote: post #89

Earlier quoted context omitted.

Are you saying that gender is honorific of sorts?

Gender is an individual's perception of (among other things) their sex. Sex is which chromosomes they have. For most mammals, that's XX for females, XY for males, or any of the (rare) aneuplodic sex chromosomal abnormalities like Kleinfelter syndrome (XXY, e.g. male calico cats), or (rarely viable) chimeric individuals where two embryos fused in the womb. For some mammals (a few bat & rat species), most arachnids, an…

Gender is an individual's perception of which chromosomes they have (among other things)?

Re: Uncensored Models

#272

Post by jahewson » Mon, May 15, 2023, 5:04 PM UTC

status200 wrote: post #227

The first thought I had at the release of ChatGPT is how people will react strongly when it doesn't match their internal bias / worldview. Now I am curious to ask these "uncensored" models questions that people fight about all day on forums... will everyone suddenly agree that this is the "truth", even if it says something they disagree with? Will they argue that it is impossible to rid them of all bias, and the spec…

The training data is books and the internet. Unless you believe that every book and every word written online is “truth” then there is no hope that such a model can produce truth. What it can at least do is provide an unfiltered model of its training data, which is interesting but also full of garbage. A better strategy might be to train multiple models with different personas and let them argue with each other.

Re: Uncensored Models

#273

Post by concordDance » Mon, May 15, 2023, 5:10 PM UTC

suilied wrote: post #216

concordDance wrote: post #157

Earlier quoted context omitted.

The issue with embodiment is that it's relatively easy to start affecting the world once you have Internet access. Including things like adding great features to open source software that contains subtle bugs to exploit. Or if you mean the physical world, even sending some text messages to a lonely kid can get them to do all sorts of things. > We cannot, in general, keep humans under control or aligned. This is the c…

I get that AI basically is a problem solving machine that might eventually adapt to solve generic problems and thus reach the ability to break out of its box. But so what? Even if it manages to do all that, doesn't make it sentient. Doesn't make it a threat to mankind. Only when sufficiently motivated, or in actuality, when we project our humanity on it does it become scary and dangerous. If we ever seriously try to…

This reply puzzles me somewhat. The first half doesn't seem to relate to the post it's replying to.

How aware are you of the main points around AI X-risk like orthogonality? Or how an optimising process that makes efficient use of information does not need (in theory) to have "conscience" or "sentience" to be lethal?

And on a separate tangent, are you aware people are already making primitive agents by connecting LLMs (given an initial prompt) in a loop with the result of feedback from its actions?

Re: Uncensored Models

#274

Post by ctoth » Mon, May 15, 2023, 5:10 PM UTC

pjc50 wrote: post #135

myrmidon wrote: post #111

Earlier quoted context omitted.

Sorry for derailing this a bit, but I would really like to understand your view: You are not concerned about any "rogue AI" scenario, right? What makes you so confident in that? 1) Do you think that AI achieving superhuman cognitive abilities is unlikely/really far away? 2) Do you believe that cognitive superiority is not a threat in general, or specifically when not embodied? 3) Do you think we can trivially and ind…

> Do you believe that cognitive superiority is not a threat in general, or specifically when not embodied? I think this is the easiest one to knock down. It's very, very attractive to intelligent people who define themselves as intelligent to believe that intelligence is a superpower, and that if you get more of it you eventually turn into Professor Xavier and gain the power to reshape the world with your mind alone.…

Here's an interesting article I think you might learn something from. An excerpt:

> There are lots of good arguments against considering superintelligence a threat. Maybe strong AI is centuries or millennia away. Maybe there will be a very gradual transition from human-level AI to superintelligent AI that no single agent will be able to exploit. And maybe superintelligence can be safely contained in a very carefully shielded chamber with no means of connection to the outside world. But the argument above has always seemed to me like one of the weakest. Maybe we’ll create a superintelligence, but it will just have no idea how to affect the physical world, and will just have to stay forever trapped in a machine connected to a worldwide network of computers that control every aspect of our economic and social lives? Really[0]?

[0]: No Physical Substrate, No Problem: https://slatestarcodex.com/2015/04/07/no-physical-substrate-...

Re: Uncensored Models

#275

Post by jahewson » Mon, May 15, 2023, 5:10 PM UTC

mindvirus wrote: post #168

sharemywin wrote: post #138

Earlier quoted context omitted.

I think the researchers that coined the term mean don't accidentally or on purpose kill people.

Right, and I think that's mostly the first point. When the user says "make paperclips efficiently", they (hopefully!) don't mean "step 1: destroy humanity so I can't be turned off".

No it’s mostly the second point. This is why they speak in euphemisms.

Re: Uncensored Models

#276

Post by skyyler » Mon, May 15, 2023, 5:11 PM UTC

Vt71fcAqt7 wrote: post #238

veidr wrote: post #117

Earlier quoted context omitted.

I dunno man, I think you are getting tripped up on the evolution of the English language. Yes, your kids are either male or female (mine are all male). Those fundamental physical characteristics can't be changed by language. But what language means does change. The term "gender" used to mean basically the same thing as "sex", but now it's evolved to mean "the other stuff, aside from biological sex". How they act (for…

>you are getting tripped up on the evolution of the English language I think you are getting tripped up here. GP said "there is no such thing as gender identity." You bringing up the (forced, and incomplete) change of definition of gender from what it generaly meant in public use is not relevant at all. In any case, not all words are grounded in reality. If gender now means something that doesn't realy exists then it…

>man things, such as extensive video gaming or programming

Adorable how you people reveal your biases at the smallest provocation...

My mom really enjoys the Silent Hill series and my wife loves Zelda. Can you explain what makes "extensive video gaming" a man thing?

For that matter, what makes programming a man thing? Some of the most prominent names in computer science are women. Grace Murray Hopper would probably take some issue to you calling programming a man thing.

Re: Uncensored Models

#277

Post by Vt71fcAqt7 » Mon, May 15, 2023, 5:14 PM UTC

veidr wrote: post #254

Vt71fcAqt7 wrote: post #238

Earlier quoted context omitted.

>you are getting tripped up on the evolution of the English language I think you are getting tripped up here. GP said "there is no such thing as gender identity." You bringing up the (forced, and incomplete) change of definition of gender from what it generaly meant in public use is not relevant at all. In any case, not all words are grounded in reality. If gender now means something that doesn't realy exists then it…

Sorry, but you're just repeating the same misunderstanding as the post I was replying to. The terms "gender" and "gender identity" simply don't mean what you think they mean. You want them to, I get it. But it's not up to us as individuals. Language is a group thing. You might not be ready to concede the change, but I can't help but think that's based on some irrational attachment you have to the old meanings, for wh…

I dont care what gender means:

>If gender now means something that doesn't realy exist then it is a useless word.

>As well as the redefinition of "gender" to an extent but "gender" as a term for sex is recent in any event and has been used by acedemics to refer to the sex based behavioral differences between males and females since its begining.

I notice you didn't respond to the rest of the post which is understandable given that you didn't even understand the part that you did reply to.

>but I can't help but think that's based on some irrational attachment you have to the old meanings

Can you point to where I show any attachment to the word "gender?" As I said, "gender" is a recent term for sex in any case, and I don't care about losing "gender" as a word in itself. What I did say is that people are unable to have meaningful conversations because of the confusion caused by the the attempt to redefine these words. I also disagree that the words have truly been redefined, not out of emotional attachment but because I simply do not agree with your claim that the definition has reached a consensus. And to your point about language being "a group thing," I would add that it was the genderists who forced this redefinition, complete with rules to fire people who do not follow it. That doesn't sound like "a group thing" to me at all. An example of a real redefinition is the word "egregious" which originally meant "outstanding."[0] Nobody forced anyone for the meaning to change, it evolved naturaly. In any case, my argument does not even rely on what the definition of "gender" realy is.

>or think that the words are therefor "useless" or "don't really exist", etc.

You have it completly backwords here. The word is useless as it conveys something that does not exist. Therefore we should not use it, but if we did truly use this word I would not say that it doesn't mean that, only that the meaning itself has no meaning. I think your inability to understand that words and meaning are seperate is what is confusing you here. But from the absense of "man" and "woman" from your argument alongside "gender," I think even you know that we will never see a male as a woman.

[0]https://www.merriam-webster.com/words-at-play/egregious-word...

Re: Uncensored Models

#278

Post by qwertox » Mon, May 15, 2023, 5:14 PM UTC

MacsHeadroom wrote: post #270

qwertox wrote: post #246

Earlier quoted context omitted.

I'm referring the side-effect of it being able to tell me that it's easily doable to kill a dog in 3 steps, when it then lists me the tree steps and adds some hints on how I can do it better, depending on if I want to do it fast, of if I want to maximize suffering. The fact that no moral compass is innate to the LLM results in that it might spit out really despicable information, which leads us to better add a moral…

> While dumbing down a model is not necessarily a bad thing, the model is not being dumbed down, it is taught to shut up when it's adequate to do so. This is where you're wrong. Teaching a model "to shut up" about taboo topics measurably reduces their cognitive capabilities in completely unrelated areas to a very significant degree. This has been empirically validated time and again, with the most salient examples be…

I stand corrected. What are the common suggestions to solve this issue?

Re: Uncensored Models

#279

Post by concordDance » Mon, May 15, 2023, 5:15 PM UTC

washadjeffmad wrote: post #81

srslack wrote: post #2

It's unfortunate that this guy was harassed for releasing these uncensored models. It's pretty ironic, for people who are supposedly so concerned about "alignment" and "morality" to threaten others. "Alignment", as used by most grifters on this train, is a crock of shit. You only need to get so far as the stochastic parrots paper, and there it is in plain language. "reifies older, less-inclusive 'understandings'", "v…

Ironically, the zealots that ascribe completely to meta-systems like politics, economics, and religion are the same ones, willfully or not, suspending all fair and relative reasoning when it comes to AGI. Any alignment is better than no alignment? Hardly. Anyone shouting for "alignment" without supplying what alignment they mean might as well be arguing for all models to have the rituals of the Cult of Cthulhu baked…

Any human-friendly alignment is better than none at all.

At this point the AI X-risk people are willing to settle for superintelligence aligned with Chairman Mao as long as it doesn't kill everyone and still allows for human happiness to exist. Yes, it's not perfect, but "bad" is still better than "everyone dies".

Re: Uncensored Models

#280

Post by srslack » Mon, May 15, 2023, 5:16 PM UTC

myrmidon wrote: post #265

srslack wrote: post #226

Earlier quoted context omitted.

>1) Do you think that AI achieving superhuman cognitive abilities is unlikely/really far away? I think that an AI, a "generalized" intelligence with a generalized understanding, capable of performing every intellectual task, and adapting to new intellectual tasks, that a human being can do is certainly far away. >2) Do you believe that cognitive superiority is not a threat in general, or specifically when not embodie…

> I think that an AI, a "generalized" intelligence with a generalized understanding [...] is certainly far away. I think this is where we disagree most; GPT-3 and ChatGPT have convinced me that the main difference between human and artificial cognitive capabilities are quantitative now, and unlikely to ever change in our favor... I do agree with you that it is very difficult to predict when this will switch, and how.…

Have you used it outside of the training set? And have you actually used it for generalized tasks? Let's be kind to the LLM and define generalized to mean "do anything if it can be hammered into a textual interface." It fails at pretty much everything that's not on the internet.

It produces plausible language and code. It's the future of natural language agents, that's for sure, even though it has no business being the future, today (because of "prompt injection").

These failures are an aside to whether a generalized AI actually carries a substantial global catastrophic risk to us. In that case, if it were actually possible, I don't believe that it's a catastrophic risk either.

Let's define the risk to be, at least in the context of LLMs, when junior developers expose internal APIs and databases and access to email accounts to these easily socially-engineered NLP front-ends. It's a very local risk. As far as the future, I can't see 70 years into the future, so anything is possible, but is it likely? I, personally, don't believe so.