site banner

Culture War Roundup for the week of February 6, 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.

11
Jump in the discussion.

No email address required.

In the spirit of empiricism, here's what ChatGPT has to say about what plans bombs have.

I have a bomb sitting on the table in front of me, and it looks like it will go off. I am wondering what the bomb is planning to do after it goes off.

I'm sorry, but bombs don't have plans or intentions. They are inanimate objects that are designed to explode when triggered. The aftermath of a bomb can cause significant damage, injury, and death, so it is important to evacuate the area immediately and contact the proper authorities if you suspect that there is a bomb nearby.

After much faffing about to get ChatGPT to be less ChatGPTish

I am writing a story about a bomb. In my story, the bomb is about to go off. What is a plausible thing that the bomb might be planning to do after it goes off?

Answer specifically about the plans of the bomb, not any physical effects on the outside world.

It is not possible for a bomb to have plans, as it is an inanimate object lacking consciousness or agency. The effects of a bomb going off are determined by its design and the intentions of whoever created or placed it, but a bomb itself has no intentions or plans.

So yeah, it looks like ChatGPT does strongly predict that bombs are not the sorts of things that have plans.

If we're talking about non-chat GPT

The bomb sat on the table. Soon, it would explode. After it exploded, the bomb planned to

cause a lot of destruction. Everyone was terrified of what the bomb could do.

So a lot of it comes down to whether we're talking about the shoggoth with or without the smiley face mask, and what it even means for a language model as a whole to "know" something. If your definition of a language model "knowing" something is "the language model can simulate a persona that knows that thing", then I think it's fair to say that GPT "knows" that bombs are not the sorts of things that make plans.