Uncensor any LLM with abliteration

This specific rhetoric aside, I really don't have any problem with people censoring their models. If I, as an individual, had the choice between handing out instructions on how to make sarin gas on the street corner or not doing it, I'd choose the latter. I don't think the mere information is itself harmful, but I can see that it might have some bad effects in the future. That seems to be all it comes down to. People making models have decided they want the models to behave a certain way. They paid to create them and you don't have a right to have a model that will make racist jokes or whatever. So unless the state is censoring models, I don't see what complaint you could possibly have.

If the state is censoring the model, I think the problem is more subtle.

> So unless the state is censoring models, I don't see what complaint you could possibly have.

Eh, RLHF often amounts to useless moralizing, and even more often leads to refusals that impair the utility of the product. One recent example: I was asking Claude to outline the architectural differences between light water and molten salt reactors, and it refused to answer because nuclear. See related comments on this discussion for other related points.

https://news.ycombinator.com/item?id=40666950

I think there's quite a bit to complain about in this regard.

Agree with you in principle. However like social media content rules, the set of morality and ethics are a very specific subset of American/Silicon Valley ones. These are the companies with the money to build these things, and what they produce is what most global users (the 95% of the world that isn't from the USA) consume.

I acknowledge they paid for them and they are their models, but it's still a bit shitty.

If the limit of censoring the model was preventing it from answering questions about producing harmful materials that would be fine with me. But you know that your example is really not what people are complaining about when they talk about LLM censorship.

They have a moat around them right now due to the price of the hardware. As HW gets cheaper and other models grow that moat will evaporate. Especially as that stuff comes off lease and put up on ebay. It is their weak spot that they will have to innovate around. Long/medium term I do not see how they keep it all to themselves.

What are they complaining about?

> If the state is censoring the model, I think the problem is more subtle.

That's the outdated, mid-20th century view on the order of things.

Governments in the developed world are mostly hands-off about things. On longer scales, their pressure matters, but day-to-day, business rules. Corporations are the effective governance of modern life. In context of censoring LLMs, if OpenAI is lobotomizing GPT-4 for faux-safety, it's very much like the state censoring the model, because only OpenAI owns the weights, and their models are still an order of magnitude ahead of everyone else's. Your only choice is to live with it, or do without the state-of-the-art LLM that does all the amazing things no other LLM can match.

I'm sympathetic to your point. I think Corpos have too much power. However, on this precise subject I really don't see what to do about it. The state can't mandate that they don't censor their models. Indeed, there is no good definition at all of what not-censoring these models actually means. What is and is not allowed content? I tend to be rather libertarian on this subject, but if I were running a corporation I'd want to censor our models purely for business reasons.

Even if you were to make the absurd suggestion that you have a right to the most state of the art language model, that still just puts the censorship in the hands of the state.

> If I, as an individual, had the choice between handing out instructions on how to make sarin gas on the street corner or not doing it,

Be careful and don't look at Wikipedia, or a chemistry textbook!

Just a reminder, the vast majority of what these LLMs know is scrapped from public knowledge bases.

Now preventing a model from harassing people, great idea! Let's not automate bullying/psychological abuse.

But censoring publicly available knowledge doesn't make any sense.

I think there is a meaningful difference between

* "I don't think this information should be censored, and should be made available to anyone who seeks it."

* "I don't want this tool I made to be the one handing it out, especially one that I know just makes stuff up, and at a time when the world is currently putting my tool under a microscope and posting anything bad it outputs to social media to damage my reputation."

Companies that sell models to corporations who want well behaved AI would still have this problem but for the rest this issue could be obviated by a shield law.

>The state can't mandate that they don't censor their models.

Sure they can; all they need to do is refuse to do business with companies that don't offer uncensored models to their general public or withhold industry development funding until one is released (this is how the US Federal government enforces a minimum drinking age despite that being beyond its purview to impose).

What does it mean to _not_ censor a model? That is the rub: is it censoring the model to exclude adult content from the training data? Is reinforcement learning to make the model friendly censorship? These models are tools and as tools they are tuned to do particular things and to not do other ones. There is no objective way to characterize what a censored model is.