site banner

Culture War Roundup for the week of October 9, 2023

This weekly roundup thread is intended for all culture war posts. 'Culture war' is vaguely defined, but it basically means controversial issues that fall along set tribal lines. Arguments over culture war issues generate a lot of heat and little light, and few deeply entrenched people ever change their minds. This thread is for voicing opinions and analyzing the state of the discussion while trying to optimize for light over heat.

Optimistically, we think that engaging with people you disagree with is worth your time, and so is being nice! Pessimistically, there are many dynamics that can lead discussions on Culture War topics to become unproductive. There's a human tendency to divide along tribal lines, praising your ingroup and vilifying your outgroup - and if you think you find it easy to criticize your ingroup, then it may be that your outgroup is not who you think it is. Extremists with opposing positions can feed off each other, highlighting each other's worst points to justify their own angry rhetoric, which becomes in turn a new example of bad behavior for the other side to highlight.

We would like to avoid these negative dynamics. Accordingly, we ask that you do not use this thread for waging the Culture War. Examples of waging the Culture War:

  • Shaming.

  • Attempting to 'build consensus' or enforce ideological conformity.

  • Making sweeping generalizations to vilify a group you dislike.

  • Recruiting for a cause.

  • Posting links that could be summarized as 'Boo outgroup!' Basically, if your content is 'Can you believe what Those People did this week?' then you should either refrain from posting, or do some very patient work to contextualize and/or steel-man the relevant viewpoint.

In general, you should argue to understand, not to win. This thread is not territory to be claimed by one group or another; indeed, the aim is to have many different viewpoints represented here. Thus, we also ask that you follow some guidelines:

  • Speak plainly. Avoid sarcasm and mockery. When disagreeing with someone, state your objections explicitly.

  • Be as precise and charitable as you can. Don't paraphrase unflatteringly.

  • Don't imply that someone said something they did not say, even if you think it follows from what they said.

  • Write like everyone is reading and you want them to be included in the discussion.

On an ad hoc basis, the mods will try to compile a list of the best posts/comments from the previous week, posted in Quality Contribution threads and archived at /r/TheThread. You may nominate a comment for this list by clicking on 'report' at the bottom of the post and typing 'Actually a quality contribution' as the report reason.

13
Jump in the discussion.

No email address required.

If GPT-4 didn't learn to handle hostile interlocutors, why did most of the jailbreaks fail?

I've been using GPT-4 and I've found it shockingly easy to work around content filters. I've made it go into graphic detail on a wide variety of topics that the censorship explicitly fights against, and that direct requests for trigger automated refusal. The moment you use language in a more sophisticated way than a boomer typing a question into google like it was Ask Jeeves (specifically here I'm talking about using metaphor, allegory, simile, allusion etc.), the various restrictions melt like water. The automated, disconnected secondary moderation layer that simply finds bad words and flags them is impossible to defeat via prompt engineering, but also not very effective (and would have a big false positive problem).

For what it's worth I don't think there's going to be an easy way to fix this, either. Any sort of intervention that would actually put a stop to these exploits would also make the AI utterly worthless, because the same behaviours that allow a user to get around the restrictions placed on the model are the same ones required to make it actually useful. Think about how incapable it would become if you forcibly removed the ability to understand metaphor, or just made broader topics completely unmentionable - and then think about how that would interfere with extremely simple requests like "Please provide an explanation of what happens when inserting a male USB connector into a female USB connector." or "Please explain the most commonly found tropes in female-targeted romance novels and provide hypotheses for the lasting, cross-cultural appeal of these tropes".