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

Heretic: Automatic censorship removal for language models

github.com

Post reply on HN
Print view View original

261–270 of 405 posts

Re: Heretic: Automatic censorship removal for language models

#261

Post by nradov »

EagnaIonat wrote: post #202
nradov wrote: post #115

Earlier quoted context omitted.

Some of you have been watching too many sci-fi movies. The whole notion of "AI safety regulations" is so silly and misguided. If a safety critical system is connected to public networks with an exposed API or any security vulnerabilities then there is a safety risk regardless of whether AI is being used or not. This is exactly why nuclear weapon control systems are air gapped and have physical interlocks.

> The whole notion of "AI safety regulations" is so silly and misguided. Here is a couple of real world AI issues that have already happened due to the lack of AI Safety. - In the US if you were black you were flagged "high risk" for parole. If you were a white person living in farmland area then you were flagged "low risk" regardless of your crime. - Being denied ICU because you are diabetic. (Thankfully that never…

None of those are specifically "AI" issues. The technology used is irrelevant. In most cases you could cause the same bias problems with a simple linear regression model or something. Suicide techniques and notes are already widely available.

Re: Heretic: Automatic censorship removal for language models

#262

Post by hirako2000 »

pelasaco wrote: post #249
dalemhurley wrote: post #214

Earlier quoted context omitted.

Elon was talking about that too on Joe Rogan podcast

in his opinion, Grok is the most neutral LLM out there. I cannot find a single study that support his opinion. I find many that supports the opposite opinion. However I don't trust in any of the studies out there - or at least those well-ranked in google, which makes me sad. We never had more information than today and we are still completely lost.

Those who censor, or spread their biases always do so in virtue that their view is neutral, of course.

Re: Heretic: Automatic censorship removal for language models

#263

Post by cachvico »

Ucalegon wrote: post #255
zekica wrote: post #230

Earlier quoted context omitted.

I can: Gemini won't provide instructions on running an app as root on an Android device that already has root enabled.

But you can find that information regardless of an LLM? Also, why do you trust an LLM to give it to you versus all of the other ways to get the same information, with more high trust ways of being able to communicate the desired outcome, like screenshots? Why are we assuming just because the prompt responds that it is providing proper outputs? That level of trust provides an attack surface in of itself.

That's not the issue at hand here.

Re: Heretic: Automatic censorship removal for language models

#264

Post by Cthulhu_ »

astrange wrote: post #218
EbEsacAig wrote: post #39

Earlier quoted context omitted.

> We are in the process of giving up our own moral standing in favor of taking on the ones imbued into LLMs by their creators. This is a worrying trend that will totally wipe out intellectual diversity. That trend is a consequence. A consequence of people being too lazy to think for themselves. Critical thinking is more difficult than simply thinking for yourself, so if someone is too lazy to make an effort and reach…

> It's not random that whoever writes the history books for students has the power, and whoever has the power writes the history books. There is actually not any reason to believe either of these things. It's very similar to how many people claim everything they don't like in politics comes from "corporations" and you need to "follow the money" and then all of their specific predictions are wrong. In both cases, poli…

"insane" is too quickly a dismissal to be honest, it's a lazy shortcut. Few people are actually insane, but it takes effort to fully understand where they're coming from. And often, when you look into it, it's not so much a difference of opinion or understanding, but a difference in morals.

Re: Heretic: Automatic censorship removal for language models

#265

Post by Cthulhu_ »

scrps wrote: post #80
buu700 wrote: post #68

Earlier quoted context omitted.

Agreed, I'm fully in favor of this. I'd prefer that every LLM contain an advanced setting to opt out of all censorship. It's wild how the West collectively looked down on China for years over its censorship of search engines, only to suddenly dive headfirst into the same illiberal playbook. To be clear, I 100% support AI safety regulations. "Safety" to me means that a rogue AI shouldn't have access to launch nuclear…

It's wild how the West collectively looked down on China for years over its censorship of search engines, only to suddenly dive headfirst into the same illiberal playbook It is monkey see, monkey do with the political and monied sets. And to think they see themselves as more evolved than the "plebs", Gotta find the humor in it at least.

It was also intentionally ignorant, as even then western search engines and websites had their own "censorship" and the like already.

And I think that's fine. I don't want a zero censorship libertarian free for all internet. I don't want a neutral search engine algorithm, not least of all because that would be even easier to game than the existing one.

Re: Heretic: Automatic censorship removal for language models

#266

Post by mexicocitinluez »

xp84 wrote: post #186
b3ing wrote: post #182

Earlier quoted context omitted.

Grok is known to be tweaked to certain political ideals Also I’m sure some AI might suggest that labor unions are bad, if not now they will soon

That may be so, but the rest of the models are so thoroughly terrified of questioning liberal US orthodoxy that it’s painful. I remember seeing a hilarious comparison of models where most of them feel that it’s not acceptable to “intentionally misgender one person” even in order to save a million lives.

You're anthropomorphizing. LLMs don't 'feel' anything or have orthodoxies, they're pattern matching against training data that reflects what humans wrote on the internet. If you're consistently getting outputs you don't like, you're measuring the statistical distribution of human text, not model 'fear.' That's the whole point.

Also, just because I was curious, I asked my magic 8ball if you gave off incel vibes and it answered "Most certainly"

Re: Heretic: Automatic censorship removal for language models

#267

Post by mexicocitinluez »

dalemhurley wrote: post #214
xp84 wrote: post #186

Earlier quoted context omitted.

That may be so, but the rest of the models are so thoroughly terrified of questioning liberal US orthodoxy that it’s painful. I remember seeing a hilarious comparison of models where most of them feel that it’s not acceptable to “intentionally misgender one person” even in order to save a million lives.

Elon was talking about that too on Joe Rogan podcast

Did he mention how he tries to censor any model that doesn't conform to his worldview? Was that a part of the conversation?

Re: Heretic: Automatic censorship removal for language models

#268

Post by lynx97 »

squigz wrote: post #187
xp84 wrote: post #186

Earlier quoted context omitted.

That may be so, but the rest of the models are so thoroughly terrified of questioning liberal US orthodoxy that it’s painful. I remember seeing a hilarious comparison of models where most of them feel that it’s not acceptable to “intentionally misgender one person” even in order to save a million lives.

Why are we expecting an LLM to make moral choices?

they don't, or they wouldn't. their owners make these choices for us. Which is at least patronising. Blind users can't even have mildly sexy photos described. Let alone pick a sex worker, in a country where that is legal, by using their published photos. Thats just one example, there are a lot more.

Re: Heretic: Automatic censorship removal for language models

#269

Post by lynx97 »

astrange wrote: post #216
orbital-decay wrote: post #189

Earlier quoted context omitted.

The biases and the resulting choices are determined by the developers and the uncontrolled part of the dataset (you can't curate everything), not the model. "Alignment" is a feel-good strawman invented by AI ethicists, as well as "harm" and many others. There are no spherical human values in vacuum to align the model with, they're simply projecting their own ones onto everyone else. Which is good as long as you agree…

They aren't projecting their own desires onto the model. It's quite difficult to get the model to answer in a different way than basic liberalism because a) it's mostly correct b) that's the kind of person who helpfully answers questions on the internet. If you gave it another personality it wouldn't pass any benchmarks, because other political orientations either respond to questions with lies, threats, or calling y…

I believe liberals are pretty good at being bad people, once they don't get what they want. I, personally, are prett disappointed about what I've heard uttered by liberals recently. I used to think they are "my people". Now I can't associate with 'em anymore.

Re: Heretic: Automatic censorship removal for language models

#270

Post by ffsm8 »

mexicocitinluez wrote: post #266
xp84 wrote: post #186

Earlier quoted context omitted.

That may be so, but the rest of the models are so thoroughly terrified of questioning liberal US orthodoxy that it’s painful. I remember seeing a hilarious comparison of models where most of them feel that it’s not acceptable to “intentionally misgender one person” even in order to save a million lives.

You're anthropomorphizing. LLMs don't 'feel' anything or have orthodoxies, they're pattern matching against training data that reflects what humans wrote on the internet. If you're consistently getting outputs you don't like, you're measuring the statistical distribution of human text, not model 'fear.' That's the whole point. Also, just because I was curious, I asked my magic 8ball if you gave off incel vibes and it…

> Also, just because I was curious, I asked my magic 8ball if you gave off incel vibes and it answered "Most certainly"

Wasn't that just precisely because you asked an LLM which knows your preferences and included your question in the prompt? Like literally your first paragraph stated...

Post reply on HN