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.

DALL-E 3 can understand semantics for multiple characters engaging in different actions, even if it's not quite as aesthetic as Midjourney.

By chance, I tried it a lot of times (through Bing) recently for two characters, a man and a woman. It's pretty bad at doing this. It keeps giving both characters the hair color I specified for one, and gives the man a bag when I specifiy the woman has a handbag. "Holding nothing" doesn't affect this. "Holding a ball of fog" tended to produce fog anywhere in the picture half the time. Also, a woman with a dress had to be specified as Caucasian to prevent the word "white" from being applied to the dress.

I fully concede it's not perfect, but if you compare it to prior models, you'll see it's a massive leap forward.

If I had to roughly quantify it, I'd say that about 2/4 of the pictures are what you asked for if you wanted a particular combination of 2 or 3 entities engaging in different activities. DALL-E 2 Experimental was maybe 1 in 16, and that was a pretty good model.

For MJ, and even SD, it's closer to random chance for getting something accurate.

If you can share an example prompt, I think I know a few tricks to getting it to understand which character or object you're referring to, it's mostly as simple as referring to the specific object directly, when you add more qualifiers.