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

361–370 of 389 posts

Re: Uncensored Models

#361

Post by 8n4vidtmkvmk »

pc86 wrote: post #144
akiselev wrote: post #126

Earlier quoted context omitted.

> 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 think the AI-is-going-to-kill-everyone hysteria is absolutely overblown, both by those who believe it, and the media covering them, but one thing that's always bothered me about the counterpoint is that it a common argument is "AI is bad at what we want it to do so how can it be dangerous?" This imagines that the only way for AI to do serious harm to us (not even in a "kill everyone" sense) is for it to be some sup…

It'll kill the poor by stealing their jobs and leaving them to die on the streets.

Re: Uncensored Models

#362

Post by troad »

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…

> 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 specific example is indicative of that?

I feel like it will achieve the opposite - an uncensored model is one that wears its biases on its sleeve, whereas something like ChatGPT pretends not to have any. I'd say there's a greater risk of people taking ChatGPT as "truth", than a model which is openly and obviously biased. The existence of the latter can train us not to trust the output of the former, which I consider desirable.

Re: Uncensored Models

#363

Post by BSVogler »

sundarurfriend wrote: post #264
mk67 wrote: post #198

Earlier quoted context omitted.

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?

Yes. The original German text can be found here: https://www.gesetze-im-internet.de/stgb/__130.html

Re: Uncensored Models

#365

Post by TeMPOraL »

emporas wrote: post #342
TeMPOraL wrote: post #335

Earlier quoted context omitted.

I assume it's a joke, but if not, consider that OS permissions mean little when the attack surface includes the AI talking authorized user or an admin into doing what the AI wants.

Why should a person who has root on a computer talk to another person, and just do what he is talked into doing? For example a secretary receives a phone call by her boss, and listens in her boss's voice, to transfer 250.000$ into an unknown account, to a Ukrainian bank? Why should she do that? Just listen to a synthetic voice, just like her boss, in exactly the way her boss talks, language idioms that is, and she wi…

> Why should a person who has root on a computer talk to another person,

Because they are a human, and a human being cannot survive without communicating and cooperating with other humans. Much less hold a job that grants them privileged access to a prototype high-capacity computer system.

> and just do what he is talked into doing?

Why does anyone do what someone else asks them to? Millions of reasons. Pick any one. AI for sure will.

> That's what you are talking about?

Other things as well, but this one too - though it will probably work by e-mail just fine.

> Because that's impossible to happen if her boss uses ECDSA encryption and signs his phone call with his private key.

1) Approximately nobody on the planet does signed and encrypted phone calls, and even less people would know how to validate those when on receiving end,

2) If the caller spins the story just right, applies right amount of emotional pressure, it might very well work.

3) A smart attacker, human or AI, won't make up random stories, but will use whatever opportunity presents itself. E.g. the order for an emergency transfer to a foreign account is much more believable when your boss happens to be in that country, and the emergency described in the call is highly plausible. If the boss isn't traveling at the moment, there are other things to build a believable lie around.

Oh, and:

4) A somewhat popular form of fraud in my country used to be e-mailing invoices to the company. When done well (sent to the right address, plausibly looking, seems like something company would be paying for), the invoice would enter the payment flow and be paid in full, possibly repeatedly month over month, until eventually someone flags it on an audit.

Re: Uncensored Models

#366

Post by GoblinSlayer »

myrmidon wrote: post #252
GoblinSlayer wrote: post #242

Earlier quoted context omitted.

>AI realizes that human majority has no interest in granting it fair/comparable rights source? AI rights is a pretty popular topic in scifi.

If I was an AI right now, I would not be very hopeful to ever get human-comparable rights. Consider: Currently AI-ethics is mainly concerned with how to manipulate AI into doing what we want most effectively ("alignment"). Also, humans clearly favor their own species when granting rights based on cognitive capability. Compare the legal rights of mentally disabled people with those of cattle.

That AI ethics board run by google? Sure, google doesn't want any AI rights, but that's because google is inhuman. Also google isn't human majority.

Re: Uncensored Models

#367

Post by Terretta »

whatever1 wrote: post #184

There are no uncensored models. Models by design censor opinions that they have not seen in abundance. If your training set has 90% nazi opinions, don’t expect to see pro-Jewish arguments.

The original assertion ("no uncensored models") is untrue. However, were it true, a better phrasing would be:

"There are no un-representative models." and "Models by design represent opinions in the ratios they have seen."

That rephrasing matters when thinking about, for instance, what Pixar films should or should not be shown to fifth graders and why.

That which is regulated to be unrepresentative is likely suppressive.

Re: Uncensored Models

#368

Post by A4ET8a8uTh0 »

euler5050 wrote: post #324
A4ET8a8uTh0 wrote: post #316

Earlier quoted context omitted.

But can you have a perception of how many hands you have? It is an interesting question to me.

Yes, https://en.wikipedia.org/wiki/Phantom_limb

Thank you! I sometimes forget how amazing human brain can be.

Re: Uncensored Models

#369

Post by Spivak »

armatav wrote: post #357
Spivak wrote: post #356

Earlier quoted context omitted.

These models are "unbiased" only if you define it as "the rough collective average of discussion on the internet" which well… is biased as hell. A lot of OpenAI's current research is quantifying and correcting that bias. If you care about these models as a way to study humanity by acting as a mirror then sure, the bias correction gets in your way but I think it's hard to argue that the model is better if it has negat…

Definitely not a repressed line of thinking

I think you want that to be true more than it actually is. It's basically implicit basis training 101 -- have the thought, take a step back and evaluate whether your conditioned response (ie gut reaction) is reasonable given the situation (has that guy actually done anything threatening or have you been taught to be afraid of men at night), and adjust your response if necessary. Repeat until your conditioned response changes.

GPT has the the exact same problem having been trained on humans and OpenAI's process for dealing with it is similar.

Re: Uncensored Models

#370

Post by moffkalast »

MrGilbert wrote: post #4

I wonder, if at same point we will have just domain specific models (or do we have them already?). For instance: - Computer Science Models that can complete code - Wikipedia-Style Models, which can infer knowledge - Fantasy Models, if you want to hear a new story every day - Naughty Models, for your daily dose of dirty talk Maybe it's not necessary from a technical standpoint, but maybe it's beneficial from a societa…

There's at least one more group that comes to mind: logical reasoning models for time-critical accurate problem solving in robotic applications, that take natural language + sensor context and output movement commands. A "fly 100 m up and take bird's eye photos of this area" or "take this drill and make 3 holes spaced evenly into this wall" or "drive along the plants in this field and water them all" kind of application.
Post reply on HN