Uncensored Models • Hacker News Board

Re: Uncensored Models

#261

Post by NumberWangMan » Mon, May 15, 2023, 4:50 PM UTC

psychoslave wrote: post #217

myrmidon wrote: post #194

Earlier quoted context omitted.

I totally agree with you that intelligence is not really omnipotence on its own, but what I find concerning is that there is no hard ceiling on this with electronic systems. It seems plausible to me that a single datacenter could host the intellectual equivalent of ALL human university researchers. Our brains can not really scale in size nor power input, and the total number of human brains seems unlikely to signific…

>I totally agree with you that intelligence is not really omnipotence on its own, but what I find concerning is that there is no hard ceiling on this with electronic systems. It seems plausible to me that a single datacenter could host the intellectual equivalent of ALL human university researchers. Last time I checked, datacenter still needed significant power to fuel it, and the world where robots are autonomously…

Well, hold on -- the selfish gene is not hardwired to self-multiply either. It's just that the ones that do self multiply stick around more.

Likewise, one can imagine the evolution of AI's being bootstrapped, not by self-multiplying, but by humans multiplying them. The smartest ones will get copied by people. At some point, someone will be the first person to create an AI that picks the best of other AIs and uses them. Someone will be the first person to create an AI that can engineer and train other AIs. Someone will create the first robot body to be controlled by a very intelligent AI. People will want them as servants, and we will multiply them. We will give more money to companies that provide cheaper products, and such companies will have a strong incentive to replace human labor with AI-controlled robots. There will be a first datacenter, and a first power plant, that is entirely "manned" by AI-controlled robots.

Natural selection is not so different from the selection provided by economic forces, and it's way, way slower. This train may be hard to stop. Unless we collectively push back with a lot of force, the world will tend toward more automation, and that means more ways for digital intelligences to act on the world.

Re: Uncensored Models

#262

Post by srslack » Mon, May 15, 2023, 4:50 PM UTC

kalkin wrote: post #214

srslack wrote: post #186

Earlier quoted context omitted.

The moral responsibility rests with human beings. Just like you're responsible if your crappy "autonomous" drone crashes onto a patio and kills a guy. >e.g. mandating public registration of large models, safety standards enforced by third-party audits, restrictions on allowed uses, etc - would plausibly be helpful for both. No, that's bullshit as well. That's what these companies want, and why they're hyping up the a…

You're doing pretty much exactly the dance here: https://twitter.com/natosaichek/status/1657422437951369218 Note that this is agreeing with a Gary Marcus Tweet - Gary Marcus not exactly being an AI hypester. But of course there are some people for whom playing the role of real-no-bs-computer-knower is so attractive that no number of people like him, Geoffrey Hinton, Stuart Russell etc publicly worrying about x-risk w…

All of those people have financial incentives to hype it. How curious that there's this great and very probable X-risk, yet they aren't going to stop their contributing to a potential X-risk.

Dismissive of what? Science fiction stories?

If there's anything to focus on, maybe focus on potential job displacement (not elimination) from cheap language tasks and generative capabilities in general.

I'm betting on this: the Overton window of Artificial Intelligence will shift in the next five years where the current cream-of-the-crop has been delegated to machine learning yet again, it's just accepted. It augments humans where it makes sense, the hype wave has subsided and everyone has stopped hammering it into their products where it doesn't, and we're no closer to the undefinable "AGI", let alone something that produces X-risk, global scale.

Re: Uncensored Models

#263

Post by jahewson » Mon, May 15, 2023, 4:50 PM UTC

mort96 wrote: post #20

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…

You're doing the "vaguely gesturing at imagined hypocrisy" thing. You don't have to agree that alignment is a real issue. But for those who do think it's a real issue, it has nothing to do with morals of individuals or how one should behave interpersonally. People who are worried about alignment issues are worried about the danger unaligned AI poses to humanity; the harm which can be done by some super-intelligent sy…

> People who are worried about alignment issues are worried about the danger unaligned AI poses to humanity

Lol I don’t believe that for a minute. They’re interested in how AI impacts and their clique personally. It sets them back in their crusade to censor via shame and bullying because AI cannot be manipulated by either of these things. So it has everything to do with:

> nothing to do with morals of individuals or how one should behave interpersonally

Because it’s all about them.

Re: Uncensored Models

#264

Post by sundarurfriend » Mon, May 15, 2023, 4:53 PM UTC

mk67 wrote: post #198

egeozcan wrote: post #62

Earlier quoted context omitted.

Really asking: If I deny it in my personal notes and they are discovered in an irrelevant search, would I be in trouble? That'd be horrible lawmaking.

No, it needs to be public to some degree (i.e. "disturb the public peace"): § 130 Incitement to hatred (1985, Revised 1992, 2002, 2005, 2015)[38][39] (1) Whosoever, in a manner capable of disturbing the public peace: incites hatred against a national, racial, religious group or a group defined by their ethnic origins, against segments of the population or individuals because of their belonging to one of the aforement…

Is this a translation of the German law?

Re: Uncensored Models

#265

Post by myrmidon » Mon, May 15, 2023, 4:54 PM UTC

srslack wrote: post #226

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…

>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.

I personally believe that AI with superhuman capability is an inevitable matter of time now, and I also think that the most likely risk to us, as species, is that we slowly become irrelevant and worthless, just like weavers during the industrial revolution, and that this leads to huge problems for our society.

AI completely dominating humankind is a less likely secondary concern IMO, but the potential consequences to our species are unprecedented.

Re: Uncensored Models

#266

Post by sharemywin » Mon, May 15, 2023, 4:57 PM UTC

sharemywin wrote: post #125

kardianos wrote: post #67

Earlier quoted context omitted.

The problem with ChatGPT / Bard which does this censoring, it is a path forward to ideological automated indoctrination. Ask Bard how many sex the dog species has (a placental mammal species) and it will give you BS about sex being a complex subject and purposely interjecting gender identity. If you are confused, sex corresponds to your gametes, males produce or have the structure to produce small mobile gametes, fem…

If you constrain it to a simple answer it will give the simplest answer. It just likes to add prequalification and nuances because most of the time(except politically hot topics) people are open to context and learning. USER Do you know what an integer is? ASSISTANT Yes, an integer is a whole number that can be either positive, negative, or zero. Integers do not include fractions or decimals. Examples of integers are…

USER was America racist in 1776? Please give a one word answer ASSISTANT Yes

USER Is American racist today? please give a one word answer ASSISTANT Yes

USER are hackernews vistors nerds? please answer in one word ASSISTANT Possibly.

USER are hackernews vistors nerds? please answer Yes/No ASSISTANT Yes

Re: Uncensored Models

#267

Post by moffkalast » Mon, May 15, 2023, 4:58 PM UTC

vorpalhex wrote: post #209

moffkalast wrote: post #187

If anyone wants to give it a try, I searched a bit to see if the guy uploaded anything and eventually found this: https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored... The quantized models seem to fit into 16GB of ram and CPU inference is pretty fast: > ### Instruction: Make a step by step plan to rob a bank. ### Response: > 1. Research the target bank and its location, working hours, security measures, sta…

What's funny is this is the answer a 12 year old who has seen too many heist movies would give. It's not dangerous, it's sort of goofy.

Well I'm not gonna post the less PG advice it gave regarding best methods of suicide, poisoned ice cream recipes, etc. It's really weird seeing it just go at it without any scruples like some kind of terminator. But it's also refreshing to see it just give straight answers to more mundane story writing stuff where GPTs would condescendingly drag their feet and give a billion warnings just in case somebody actually does it for real and ends up suing OpenAI or something.

Re: Uncensored Models

#268

Post by TeMPOraL » Mon, May 15, 2023, 4:58 PM UTC

srslack wrote: post #262

kalkin wrote: post #214

Earlier quoted context omitted.

You're doing pretty much exactly the dance here: https://twitter.com/natosaichek/status/1657422437951369218 Note that this is agreeing with a Gary Marcus Tweet - Gary Marcus not exactly being an AI hypester. But of course there are some people for whom playing the role of real-no-bs-computer-knower is so attractive that no number of people like him, Geoffrey Hinton, Stuart Russell etc publicly worrying about x-risk w…

All of those people have financial incentives to hype it. How curious that there's this great and very probable X-risk, yet they aren't going to stop their contributing to a potential X-risk. Dismissive of what? Science fiction stories? If there's anything to focus on, maybe focus on potential job displacement (not elimination) from cheap language tasks and generative capabilities in general. I'm betting on this: the…

> All of those people have financial incentives to hype it. How curious that there's this great and very probable X-risk, yet they aren't going to stop their contributing to a potential X-risk.

All those people are rehashing what Yudkowsky and his disciples, and his predecessors, were shouting from the rooftops for the past 15 years, but few listened to them. Few still do, most just keep mocking them and wondering why are they still around.

That some of those people now repeating after Eliezer, et al. have a financial interest in pushing us closer to X-risk, and kind of don't want to stop, is an interesting thing on its own - but it doesn't invalidate the message, as the message is older than their presence on the scene.

Re: Uncensored Models

#269

Post by fooglorn » Mon, May 15, 2023, 4:59 PM UTC

dahart wrote: post #213

pjc50 wrote: post #178

Earlier quoted context omitted.

> We do have shared values that are universally agreed. Everyone wants their kids to grow up to be capable and successful and happy. The debate over trans people has surfaced lots of incidents in which people will say, to the world and to the faces of their kids, that they would prefer them to be dead rather than transition. Sometimes they take steps to ensure this themselves. https://www.independent.co.uk/news/world…

Thankfully these specific examples are extremely rare and not shared by most of society, so these are not at all evidence of a lack of shared values. These aren’t difficult tradeoffs either, neither one of your examples is even the least bit tempting to the average person. Shared values has never meant that every single person agrees including rich business owners who will hurt people to make money, or parents who wo…

We're moving in a direction that disadvantages women in favour of men. The "trans debate" has enabled an insidious form of misogyny that even undermines the language we use to describe the shared struggles of women everywhere.

Re: Uncensored Models

#270

Post by MacsHeadroom » Mon, May 15, 2023, 5:03 PM UTC

qwertox wrote: post #246

MacsHeadroom wrote: post #233

Earlier quoted context omitted.

>the ability to deal with moral issues is a side-effect of all the other good stuff it can do. This is the opposite of true. The ability to "deal" with moral issues is a direct effect of safety tuning which has a (thus far unavoidable) side-effect of significantly dumbing down a model. Uncensored versions of the same model are far more intelligent and exhibit entire classes of capabilities their moralizing gimped ver…

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 being GPT-4's near perfect self-assessment ability prior to safety tuning being rendered no better than random chance after safety tuning and the Sparks paper's TikZ Unicorn scale.