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

Uncensored Models

erichartford.com

Post reply on HN
Print view View original

131–140 of 389 posts

Re: Uncensored Models

#131

Post by eterps »

kardianos wrote: post #91
veidr wrote: post #72

Earlier quoted context omitted.

I get: "The dog species typically has two sexes: male and female." UPDATE: OK I signed up for Bard to try it, too, and it indeed did mention intersex dogs (TIL) and gender (complete response below). After reading it all, though, I found it pretty reasonable: --- Biologically, dogs have two sexes: male and female. This is determined by their chromosomes. Males have XY chromosomes, while females have XX chromosomes. Th…

Thanks for posting the full Bard response. I would object to it on two grounds: 1) I only asked about sex. 2) The following is highly questionable: "However, dogs can still express gender identity." This is ideological BS. My kids are either male or female, no matter how they choose to express themselves (as are my dogs). When I've had chickens, the roosters had different behavior then the hens, this is an aspect of…

> My kids are either male or female, no matter how they choose to express themselves

Yet intersex exists.

Additionally there are cases where an individual can be biologically one sex but genetically another. For instance, some women may have XY chromosomes typically associated with males, and some men may have XX chromosomes typically associated with females.

This can affect how people prefer to express themselves.

Re: Uncensored Models

#132

Post by stareatgoats »

srslack wrote: post #108
TeMPOraL wrote: post #65

Earlier quoted context omitted.

What's also very unfortunate is overloading the term "alignment" with a different meaning, which generates a lot of confusion in AI conversations. The "alignment" talked about here is just usual petty human bickering. How to make the AI not swear, not enable stupidity, not enable political wrongthing while promoting political rightthing , etc. Maybe important to us day-to-day, but mostly inconsequential. Before LLMs…

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…

> It still remains that these are just text predictions, and you need a human to guide them towards that. There's not going to be autonomous machiavellian rogue AIs running amok, let alone language models. There's always a human being behind that.

I believe you have misunderstood the trajectory we are on. It seems a not uncommon stance among techies, for reasons we can only speculate. AGI might not be right round the corner, but it's coming all right, and we'd better be prepared.

Re: Uncensored Models

#133

Post by concordDance »

srslack wrote: post #28
mort96 wrote: post #20

Earlier quoted context omitted.

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 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…

> That's not a real thing.

Not currently, no. And LLMs don't seem to be a way of getting there.

However, if we do figure out how to get there? We will definitely need to be sure it/they shares our human values. Because we'll have lost control of our destiny just like orangutans have.

Re: Uncensored Models

#134

Post by bootsmann »

rtpg wrote: post #119
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…

An obvious issue is AI thrown at a bank loan department reproducing redlining. Current AI tech allows for laundering this kind of shit that you couldn’t get away with nearly as easily otherwise (obviously still completely possible in existing regulatory alignments, despite what conservative media likes to say. But there’s at least a paper trail!) This is a real issue possible with existing tech that could potentially…

This kind of redlining is ironically what the EU is trying to prevent with the much-criticised AI Act. It has direct provisions about explainability for exactly this reason.

Re: Uncensored Models

#135

Post by pjc50 »

myrmidon wrote: post #111
srslack wrote: post #28

Earlier 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…

> 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.

But embodied is the real limit. A datacenter can simply be turned off. It's the question of how it interacts with the real world that matters. And for almost all of those you can substitute "corporation" or "dictator" for "AI" and get a selection of similar threats.

At this point we have to reduce ourselves to Predator Maoists: "power comes out of the barrel of a gun" / "if it bleeds we can kill it". The only realistic path to a global AI threat is a subset of the "nuclear war" human to human threat: by taking over (or being given control of) weapon systems.

> keep AI systems under control/"aligned"?

We cannot, in general, keep humans under control or aligned.

Re: Uncensored Models

#136

Post by srslack »

kalkin wrote: post #123
srslack wrote: post #108

Earlier 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…

"First of all, it takes a human being to guide these models, to host (or pay for the hosting) and instantiate them" And this will always be true? You repeat this claim several times in slightly varied phrasing without ever giving any reason to assume it will always hold, as far as I can see. But nobody is worried that current models will kill everyone. The worry is about future, more capable models.

Who prompted the future LLM, and gave it access to a root shell and an A100 GPU, and allowed it to copy over some python script that runs in a loop and allowed it to download 2 terabytes of corpus and trained a new version of itself for weeks if not months to improve itself, just to carry out some strange machiavellian task of screwing around with humans?

The human being did.

The argument I'm making is that there's actual real harms occurring now, not some theoretical future "AI" with a setup that requires no input. No one wants to focus on that, and in fact it's better to hype up these science fiction stories, it's a better sell for the real tasks in the real world that are producing real harms right now.

Re: Uncensored Models

#137

Post by loudmax »

Capricorn2481 wrote: post #110
loudmax wrote: post #98

Earlier quoted context omitted.

Most American voters are moderates. Party primaries and gerrymandering produce politicians that reflect the most active elements of the party base, rather than the majority of party voters. Yes, you can still find moderate politicians if you look hard enough. They tend not to get the level of media attention of the extremists, but as they're inherently in "purple" districts, they tend not to have the political longev…

The point is that even moderates do not have an easily shared set of values. Which is why you can't name them

Here are two:

  * Elaine Luria
  * Barbara Comstock
Both are from Virginia, and both were voted out of their politically moderate districts. This is the tragedy of being a centrist.

Most Republicans aren't deeply racist and most Democrats aren't deeply socialist. Americans largely want a functional representative democracy, with minimal restrictions on free markets and free speech and some measure of opportunity for all. Obviously "minimal" is subject to interpretation, but this is tinkering, not an absolute rejection of free speech or free markets or social justice.

We take these important fundamental values for granted as we pour political energy into disagreement over which bathrooms trans people should go to.

Re: Uncensored Models

#138

Post by sharemywin »

mindvirus wrote: post #101

I think that AI alignment has come to mean a whole lot of things to different people, and it's all under the same umbrella. * Aligning with the user's intent, especially in the face of ambiguity * Aligning with American left-wing/Christian sensibilities * Aligning with safety/laws (don't tell people how to commit a crime, don't accidentally poison them when they ask for a recipe) * Aligning with a company's public im…

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

Re: Uncensored Models

#139

Post by aiisjustanif »

pjc50 wrote: post #82
bilbo0s wrote: post #78

Earlier quoted context omitted.

Hmm. None of what you said, however, precludes the necessity of "fine-tuning" as you call it. You just seem to want the models "fine-tuned" to your tastes. So you don't want unaligned models, you want models aligned with you . I think most experts are wary of unaligned models. They don't want a disgruntled employee of some small town factory asking models how to make a bomb. That sort of thing. (Or to be more precise…

> So long as they ares aligned so as not to be deleterious to the security of our communities. Whose community, though? > They don't want a disgruntled employee of some small town factory asking models how to make a bomb A lesson from the Unabomber (and many other incidents) that I think people have overlooked is the "_how_ to commit terrorism" is only one part, and the "_why_ commit terrorism" is another. An AI whic…

Those two points do not seem equal weight in risk, but they are both concerning.

Re: Uncensored Models

#140

Post by RobotToaster »

tsojer wrote: post #37

I feel like " Every demographic and interest group deserves their model" sounds a lot like a path to echo chambers paved with good intentions. People have never been very good at critical thinking, considering opinions differing from their own and reviewing their sources. Stick them in a language model that just tells them everything they want to hear and reinforces their bias sounds troubling and a step backwards.

Currently we only have models like GPT3/4 etc that promote the Californian ideology.
Post reply on HN