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

151–160 of 389 posts

Re: Uncensored Models

#151

Post by pc86 »

amluto wrote: post #103
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…

I think there are at least two broad types of thing that are characterized as “alignment”. One is like the D&D term: is the AI lawful good or chaotic neutral? This is all kinds of tricky to define well, and results in things that look like censorship. The other is: is the AI fit for purpose. This is IMO more tractable. If an AI doesn’t answer questions (e.g. original GPT-3), it’s not a very good chatbot. If it makes…

The problem with trying to tack on D&D-type alignment to something like this is that everyone presents their favored alignment as lawful good, and the other guys as - at best - lawful evil.

Re: Uncensored Models

#152

Post by ftxbro »

sharemywin wrote: post #138
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.

It's true and after this change of meaning they have tried making other names like "dont-kill-everyoneism" or "AI-not-kill-everyoneism" for it (not joking) but they are worried if it will sound too silly or alarmist or if it won't catch on. That said, language does its own evolution without regard for what the ones who coined it had meant.

Re: Uncensored Models

#153

Post by pixl97 »

leroy-is-here wrote: post #124
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…

A “superhuman” AI is just a machine, a very expensive one. It can be turned off and we control the outputs it has. Why would an AI have the ability to launch nuclear weapons unless we gave it a button? A “superhuman” intelligence is without a body, so we control any interfaces it has access to. The Internet could be accessed, but any attempt to “hack” through the Internet is met by routine packet defenses. The AI is…

Supercomputers used to be giant machines we had in giant warehouses... Now the phone in your pocket has the computing power of the 1980s walking around with you. Assuming your super intelligence will always be huge is... well not a great assumption.

Also superintelligence doesn't need a body itself. It just needs yours. Putin for example has commanded hundreds of thousands of dumbasses to go get themselves killed in Ukraine. In this case does it matter if Putin is flesh and blood, or a processor that lists out commands for others to follow as long as they are willing to listen?

Re: Uncensored Models

#154

Post by pjc50 »

srslack wrote: post #136
kalkin wrote: post #123

Earlier quoted context omitted.

"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 a…

> 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.

I generally agree with you and think the doomerists are overblown, but there's a capability argument here; if it is possible for an AI to augment the ability of humans to do Bad Things to new levels (not proven), and if such a thing becomes widely available to individuals, then it would seem likely that we get "Unabomber but he has an AI helping him maximise his harm capabilities".

> it's a better sell for the real tasks in the real world that are producing real harms right now.

Strongly agree.

Re: Uncensored Models

#155

Post by mschuster91 »

Capricorn2481 wrote: post #120
mschuster91 wrote: post #112

Earlier quoted context omitted.

Mostly these laws are scoped to the country one is living in. The problem is, say I decide to post a meme inciting violence in a different country or limiting a country's decision to join NATO (the quran burning in Sweden for example caused Turkish president Erdogan to block Sweden's NATO bid)... I don't have to face any charges or responsibility, despite potentially affecting the lives of millions of people.

You are right, and this is a tech problem even before LLMs. Facebook has allowed very consequential calls for ethnic cleansing in Ethiopia and hasn't done anything about it. That is the issue with a global tech products. But there's nothing about LLMs that changes that from a country level prosecution/accountability perspective. You still have to be aware of where you're putting that text into the world. Right now, i…

> You are right, and this is a tech problem even before LLMs.

Indeed, which is why I find statements such as the one from the article's author that I pointed out in the first comment in the chain so disgusting. "Enjoy responsibly" is not an attitude to have with a weapon so powerful as AI or social media.

Re: Uncensored Models

#156

Post by pc86 »

iNic wrote: post #128
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 clearly know nothing about the alignment field since you are throwing together two groups of people that have nothing in common. The stochastic parrot people only care about "moral" and "fair" AI, whereas the AI saftey or AI notkilleveryone people care about AI not killing everyone. Also the whole "who's value" argument is obviously also stupid, since for now we don't know how to put anybody's value into an AI. C…

No comment on whether it's broadly a good thing or bad thing, but you can't get ChatGPT (on GPT-4 at least) to tell you even slightly scandalous jokes without a lot of custom prompting and subterfuge, and they seem to be spending active development and model training time to try to counter a lot of the circumvention we've seen to get around these guardrails. Not just for dirty jokes but for anything deemed bad.

So it seems pretty clear you can load values into an LLM.

Re: Uncensored Models

#157

Post by concordDance »

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.…

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 crux of why replicable-more-than-human-intelligence is so dangerous. Even giving a random person on the street great power is a bad idea, and they've evolved to have very similar values and preferences to you.

Re: Uncensored Models

#158

Post by myrmidon »

akiselev wrote: post #126
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…

> Because I view myself ABSOLUTELY not as some kind of AI luddite, but I honestly belief that this is one of the very few credible extinction threats that we face, and I'm counting NEITHER climate change nor nuclear war in that category, for reference. This is absurd histrionics, Daily Mail CAPSLOCK and all. We’ve got signs of an unprecedented heat wave coming with ocean temperatures two standard deviations above nor…

I'm not saying climate change is not a giant problem, I'm saying it's unlikely to eradicate our species.

I believe it is dangerously shortsighted to base AI threat estimation on current self-driving performance; the two fields of advancing AI cognitive abilities and improving selfdriving are not sufficiently connected for that IMO.

We're also putting a lot of focus on system designs that are useful to us, instead of directly building potentially threatening architectures (online learning/longterm memory/direct connection + feedback from physical reality), but those could already be within our grasp technologically (maybe?).

What do you think about the 3 points I raised?

Re: Uncensored Models

#159

Post by antiterra »

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…

This is about the ‘political, legal, and PR protection’ kind of alignment to avoid news stories about kids making bombs thanks to an enthusiastically accommodating GPT. Language models are set to be the new encyclopedias— what a model presents as real is going to be absorbed as real by many people. Considering the implications of that isn’t an issue of emotional oversensitivity.

Further, there’s a case for a public facing chat assistant to be neutral about anything other than upholding the status quo. Do you want to trust the opinion of a chatbot as for when and who against an armed uprising is appropriate?

This is not really about a threat model of AGI turning our world into a dystopia or paperclips. However, your disdain for people who are being thoughtful about the future and ‘thought experiments’ seems brash and unfounded. Thought experiments have been incredibly useful throughout history and are behind things like the theory of relativity. Nuclear stalemate via mutually assured destruction is a ‘thought experiment,’ and one I’m not eager to see validated outside of thought.

Re: Uncensored Models

#160

Post by psychoslave »

>To pretend otherwise is to prove yourself an idealogue and a dogmatist.

Well, not false. Or at last, it seems we agree.

Thus said, going with so called uncensored versions is not free of ideology or dogmatism either.

There is just no "a view from nowhere". Look at how, generally speaking, all your data set are so anthropocentric.

Not to say there is anyone to blame or that there is any pretension here to utter something out of a situational perspective.

Post reply on HN