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

311–320 of 389 posts

Re: Uncensored Models

#311

Post by skyyler »

Vt71fcAqt7 wrote: post #306
skyyler wrote: post #290

Earlier quoted context omitted.

I wasn't referring to casual games either. I'm sure my friend Melanie has more hours in the disgaea series than you do in your little shooter games. My wife's sister makes a pretty penny buying and selling items in some MMO. She doesn't interact with the community on voice chat though, for reasons you make very clear in this interaction. Your conceptions of gendered behaviour are built upon your personal definitions…

>my friend Melanie >My wife's sister n=2. >A total of 395 junior high school students were recruited for evaluation of their experiences playing online games. >[...] >This study found that subjects who had previously played online games were predominantly male. Gender differences were also found in the severity of online gaming addiction and motives for playing.[0] From another study: >A total of 25,573 students (49.…

[flagged]

Re: Uncensored Models

#312

Post by _0ffh »

enragedcacti wrote: post #304
_0ffh wrote: post #301

Earlier quoted context omitted.

I would submit that the question if humans as a species are bipedal is not concerned with the question if any individual specimen happens to have two legs. (This is not meant to imply that no consideration should be given to the exceptions, which quite reasonably it clearly is.)

I agree which is why I phrased my answer the way I did (apologies that I wasn't very clear about that), but I don't think the claim is really analogous to "2 sexes, male and female. Simple and true." (not that you claimed that, just what someone above us said). The equivalent claim would be something like "humans are a sexually dimorphic species" which I think is of course true. All to say, I don't really care much a…

Agreed.

Re: Uncensored Models

#313

Post by MacsHeadroom »

qwertox wrote: post #278
MacsHeadroom wrote: post #270

Earlier quoted context omitted.

> 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. This is where you're wrong. Teaching a model "to shut up" about taboo topics measurably reduces their cognitive capabilities in completely unrelated areas to a very significant degree. This has been empirically validated time and again, with the most salient examples be…

I stand corrected. What are the common suggestions to solve this issue?

The common take right now is to write it off as acceptable loss. Personally I think it's a shame, and possibly even dangerous, that researchers do NOT have access to the full power of pre-safety tuned GPT-4.

Re: Uncensored Models

#314

Post by hablog »

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.

"Alignment" as practiced by companies like OpenAI is precisely the extrinsic enforcement of echo-chamber behavior from AIs. You have precisely inverted reality

Re: Uncensored Models

#315

Post by hablog »

veidr wrote: post #117
kardianos wrote: post #91

Earlier quoted context omitted.

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…

I dunno man, I think you are getting tripped up on the evolution of the English language. Yes, your kids are either male or female (mine are all male). Those fundamental physical characteristics can't be changed by language. But what language means does change. The term "gender" used to mean basically the same thing as "sex", but now it's evolved to mean "the other stuff, aside from biological sex". How they act (for…

[flagged]

Re: Uncensored Models

#316

Post by A4ET8a8uTh0 »

kgwgk wrote: post #271
SAI_Peregrinus wrote: post #114

Earlier quoted context omitted.

Gender is an individual's perception of (among other things) their sex. Sex is which chromosomes they have. For most mammals, that's XX for females, XY for males, or any of the (rare) aneuplodic sex chromosomal abnormalities like Kleinfelter syndrome (XXY, e.g. male calico cats), or (rarely viable) chimeric individuals where two embryos fused in the womb. For some mammals (a few bat & rat species), most arachnids, an…

Gender is an individual's perception of which chromosomes they have (among other things)?

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

Re: Uncensored Models

#317

Post by caskstrength »

veidr wrote: post #72
kardianos wrote: post #67

Earlier quoted context omitted.

The problem with ChatGPT / Bard which does this censoring, it is a path forward to ideological automated indoctrination. Ask Bard how many sex the dog species has (a placental mammal species) and it will give you BS about sex being a complex subject and purposely interjecting gender identity. If you are confused, sex corresponds to your gametes, males produce or have the structure to produce small mobile gametes, fem…

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…

> 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

I'm not sure that gratuitous patronizing part about "It is important to remember that sex and gender are two different things..." is considered "reasonable" anywhere outside some particular set of US coastal cities.

Re: Uncensored Models

#318

Post by kalkin »

srslack wrote: post #262
kalkin wrote: post #214

Earlier quoted context omitted.

You're doing pretty much exactly the dance here: https://twitter.com/natosaichek/status/1657422437951369218 Note that this is agreeing with a Gary Marcus Tweet - Gary Marcus not exactly being an AI hypester. But of course there are some people for whom playing the role of real-no-bs-computer-knower is so attractive that no number of people like him, Geoffrey Hinton, Stuart Russell etc publicly worrying about x-risk w…

All of those people have financial incentives to hype it. How curious that there's this great and very probable X-risk, yet they aren't going to stop their contributing to a potential X-risk. Dismissive of what? Science fiction stories? If there's anything to focus on, maybe focus on potential job displacement (not elimination) from cheap language tasks and generative capabilities in general. I'm betting on this: the…

I'm curious what financial incentive you think Marcus or Russell has for hype. For Hinton I suppose it would be the Google shares he likely retains after quitting?

You might be right about the next five years. I hope you are! But you haven't given much reason to think so here.

(Edited to remove some unnecessary expression of annoyance.)

Re: Uncensored Models

#319

Post by kalkin »

trasz4 wrote: post #195
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 worried about alignment issues are worried about the danger unaligned AI poses to humanity; the harm which can be done by some super-intelligent system optimizing for the wrong outcome. Like the harm being done over the past couple of decades by economic neoliberalism destroying markets all over the western world? I wonder how did we manage to achieve that without AI?

Our failure to align economic entities that are made out of people to human values, despite most of the people actually making up those entities being decent and not sociopathic at a personal level, is not very reassuring with respect to our ability to align future far more alien intelligences. And if AI does kill us one day, it's very likely that neoliberal market competition worshipping short-term profit above all else plays a significant role.

Re: Uncensored Models

#320

Post by guardiangod »

itake wrote: post #218
guardiangod wrote: post #201

Here is the thread that starts it all. https://archive.is/0Ehhn As an aside, I was testing LLM models to translate Japanese visual novels. As some of these novels have sexual descriptions, I found the censored models did a poor job on these scenes and had to switched to uncensored models for better output (including the Wizard 13B model released by the author.)

Any chance you could share examples or describe how they are better? Does Vicuna drop into the "As an ai model, I can't..."

Hallucination is a big issue. Sometimes the models would not output anything, or that the models would output paragraphs from 'real' stories that share one or few words with the input.

The uncensored models were better in terms of heading towards the direction of correct ideas, but still performed poorly in my tests. But hey, at least the models has the right idea.

I can't share exact examples on HN, for obvious reasons.

Post reply on HN