Earlier quoted context omitted.
Who's "we"?
Humanity.
Good thing we're all aligned the same way, then!
Uncensored Models
241–250 of 389 posts
Re: Uncensored Models
#242Earlier quoted context omitted.
> 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.…
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…
>AI realizes that human majority has no interest in granting it fair/comparable rights
source?
AI rights is a pretty popular topic in scifi.
Re: Uncensored Models
#243Earlier quoted context omitted.
>People who are afraid of unaligned AI aren't afraid that it will be impolite. People who are not afraid of it being impolite are afraid of science fiction stories about intelligence explosions and singularities. That's not a real thing. Not anymore than turning the solar system into paperclips. The "figurehead", if you want to call him that, is saying that everyone is going to die. That we need to ban GPUs. That onl…
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…
I am not the person you are replying to, but since I would say similar things to their original comment:
A. I see little to no evidence that LLMs are where the singularity happens
B. I see little to no evidence that (given an AGI) reinforcement learning is likely to end up with a sufficiently aligned agent.
C. In any event the OpenAI alignment is specifically restricts AI from (among other things) being "impolite" in contradiction to what mort96 says.
Alignment is a good thing to work on. I'm glad OpenAI is doing so. But attacking people for making uncensored LLMs hurts the pro-alignment case more than it helps.
Re: Uncensored Models
#244Eric white-washes aligned models as having a "liberal" or "progressive" bias as a statement of fact. I think this diminishes his argument as it denies the complexity of factors motivating alignment of language model output. Many models have alignment properties that perform the opposite: in some cases they censor or frame literal facts that malign or impugn MAGA conservatives. So I think Eric doesn't represent alignment as the painstaking, but ultimately flailing, attempt to "please everyone" that it is.
Re: Uncensored Models
#245Earlier quoted context omitted.
There is very little that is illegal to write down (with or without AI help) in most jurisdictions. Even things like threats, the crime is in the communication, not in writing the text. I can write down "Person X, I'm going to kill you dead" in my notebook as much as I want, as long as I don't communicate to anyone (i.e. threaten anyone, as opposed to writing down a threat in my personal papers). I'm very curious wha…
OP is talking about visual imagery, but even textual depictions may not be as legally safe as you think. Further reading: https://en.wikipedia.org/wiki/Legal_status_of_fictional_porn...
TL;DR: in much of the world fictional child pornography is illegal. In the US, any fictional child pornography that is indistinguishable from factual child pornography, or any child pornography that is obscene under the Miller test[1] is also illegal.
Re: Uncensored Models
#246Earlier quoted context omitted.
Why not just ask it to make a sound app? Keep in mind that the ability to deal with moral issues is a side-effect of all the other good stuff it can do.
>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 compass to the system.
The reason for this LLM to be offered is not so that it can teach us bad things, like the example I mentioned, but, for example, to help us dealing with source code, programming languages, reasoning concepts, summarization and so on.
For it to be able to offer us this, it will very likely also be capable of having the knowledge of how to kill a dog, an exhibition we should suppress. 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.
Re: Uncensored Models
#247Earlier quoted context omitted.
>People who are afraid of unaligned AI aren't afraid that it will be impolite. People who are not afraid of it being impolite are afraid of science fiction stories about intelligence explosions and singularities. That's not a real thing. Not anymore than turning the solar system into paperclips. The "figurehead", if you want to call him that, is saying that everyone is going to die. That we need to ban GPUs. That onl…
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…
Before we have to face a rouge Artificial Intelligence mankind has to face Artificial Idiocy in the form of pseudo-intelligence and people who fall for it.
Re: Uncensored Models
#248Earlier 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.…
People will make sure it is embodied. Do any of the major powers have the luxury of turning off their superhuman AI when up against that of the other powers? Definitely not. People will willingly give up control, even as they see the AI grabbing power for its own purposes, in the gamble that it still leaves them better off than dead. That means people would be the ones physically defending the data centers.
I also don’t think superhuman intelligence will need a data center. The way the models are growing in capability at the same size, combined with hardware improvements, I’m pretty sure it will fit on a single server.
Personally I’m worried about less post-apocalyptic threats. Putin using LLM’s to create a personal stream of misinformation for every voter in the U.S. is definitely a possibility for next year’s presidential elections. People are incapable of defending against the comparatively tiny amounts of human-manufactured misinformation, so imagine how poorly they would do when 90% of what they see online is generated misinformation. LLM’s have the potential of being the death of democracy, especially when combined with deepfake technology.
Re: Uncensored Models
#249Earlier quoted context omitted.
I agree with you that "AI safety" (let's call it bickering) and "alignment" should be separate. But I can't stomach the thought experiments. First of all, it takes a human being to guide these models, to host (or pay for the hosting) and instantiate them. They're not autonomous. They won't be autonomous. The human being behind them is responsible. As far as the idea of "hacking some funny Internet money, using it to…
>They're not autonomous. They won't be autonomous. https://github.com/Significant-Gravitas/Auto-GPT >This program, driven by GPT-4, chains together LLM "thoughts", to autonomously achieve whatever goal you set. As one of the first examples of GPT-4 running fully autonomously, Auto-GPT pushes the boundaries of what is possible with AI. >As an autonomous experiment, Auto-GPT may generate content or take actions that ar…
Let's ignore the fact that current state-of-the-art models will sit around and be stuck in its ReAct-CoT loop doing nothing for the most part, and when it's not doing jack shit it'll "role-play" that it's doing anything of consequence, while not really doing anything, just burning up API credits.
>existing or capable of existing independently
>undertaken or carried on without outside control
>responding, reacting, or developing independently of the whole
It fails all of those. Just because you put autonomous in the name, doesn't mean it's actually autonomous. And if it does anything of consequence, you quite literally governed it from the start with your prompt. I've run it, I know about it, I've built a much more capable browser, and assorted prompted functionalities with my own implementation. They're not autonomous.
At least it's not all of the other agentic projects on GitHub that spam emojis in their READMEs with mantras of saving the world and utilizing AI with examples that it literally can't do (they haven't figured out that whole agentic part yet.)
Don't get me wrong, I enjoy the technology. But it's quite a bit too hyped. And I just personally don't believe there's actually X-risk from future possibilities, not before 50 or 100 years out, if then. But I'm not a prophet.
Re: Uncensored Models
#250Earlier quoted context omitted.
>People who are afraid of unaligned AI aren't afraid that it will be impolite. People who are not afraid of it being impolite are afraid of science fiction stories about intelligence explosions and singularities. That's not a real thing. Not anymore than turning the solar system into paperclips. The "figurehead", if you want to call him that, is saying that everyone is going to die. That we need to ban GPUs. That onl…
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…
Think the point is "alignment" isn't doing shit about 1 and 2.