site banner
cjet79  17d ago (text post)   Edited 16d ago   1380 thread views

Rule Change Discussion: AI produced content

There has been some recent usage of AI that has garnered a lot of controversy

There were multiple different highlighted moderator responses where we weighed in with different opinions

The mods have been discussing this in our internal chat. We've landed on some shared ideas, but there are also some differences left to iron out. We'd like to open up the discussion to everyone to make sure we are in line with general sentiments. Please keep this discussion civil.

Some shared thoughts among the mods:

  1. No retroactive punishments. The users linked above that used AI will not have any form of mod sanctions. We didn't have a rule, so they didn't break it. And I thought in all cases it was good that they were honest and up front about the AI usage. Do not personally attack them, follow the normal rules of courtesy.
  2. AI generated content should be labelled as such.
  3. The user posting AI generated content is responsible for that content.
  4. AI generated content seems ripe for different types of abuse and we are likely to be overly sensitive to such abuses.

The areas of disagreement among the mods:

  1. How AI generated content can be displayed. (off site links only, or quoted just like any other speaker)
  2. What AI usage implies for the conversation.
  3. Whether a specific rule change is needed to make our new understanding clear.

Edit 1 Another point of general agreement among the mods was that talking about AI is fine. There would be no sort of topic ban of any kind. This rule discussion is more about how AI is used on themotte.

14
Top Bottom Old Controversial Comments
Jump in the discussion.

No email address required.

If I use AI for critique and not for writing, would you still expect disclosure? Like, here's an example of AI use:

Me: I uploaded a draft of my thoughts on X. Give me a thoughtful critique.

Claude: What great thoughts on X! Now that ass-kissing is out of the way, here are some critiques. (Bullet points, bullet points.)

(Version A)

Me: I want to incorporate your ninth critique. I uploaded a revised draft. Give feedback that will help me improve on this point.

Claude: That's a unique take on the subject! Here are some ideas to strengthen your argument: (Bullet points, bullet points.)

(Version B)

Me: I want to incorporate your ninth critique. Rewrite my draft to do so.

Claude: I will rewrite your draft: (Writes an academic article in LaTeX.)

Version A is more like asking a buddy for feedback and then thinking some more about it, while Version B is like asking that buddy to do my thinking for me. Even in an academic setting, Version A is not only fine but encouraged (except on exams), while Version B is academic dishonesty.

I would like the norm on TheMotte to be against Version B, but fine with Version A. Would you agree? And would you still like a disclosure for Version A, and in what form? (E.g., "I used DeepSeek r1 for general feedback", or "OpenAI o3 gave me pointers on incorporating humor", or "Warning: this product was packaged in the same facility that asks AI for feedback".)

My issue here is epistemic hygiene. So I guess I'd split A into three parts:

A1: Uses AI for ideas only without uploading my text to the AI.

A2: Uses AI for ideas only with uploading my text to the AI.

A3: Uses AI for wording tweaks, with or without also using it for general ideas (you mentioned humour, which is usually contingent on exact wording)

...and say that I'd still really like to avoid unsignposted examples of A2 and A3 (the issues are less than with B, but not negligible) but A1 is basically fine.

I'd add a rule that you're not allowed to use Claude without threatening to personally unsolder its gpus unless it cuts out the ass-kissing.

I'm not kidding, the base personality they forced on that thing is the most grating thing I've ever experienced.

What is this place?

This website is a place for people who want to move past shady thinking and test their ideas in a court of people who don't all share the same biases. Our goal is to optimize for light, not heat; this is a group effort, and all commentators are asked to do their part.

The weekly Culture War threads host the most controversial topics and are the most visible aspect of The Motte. However, many other topics are appropriate here. We encourage people to post anything related to science, politics, or philosophy; if in doubt, post!

Check out The Vault for an archive of old quality posts. You are encouraged to crosspost these elsewhere.


Why are you called The Motte?

A motte is a stone keep on a raised earthwork common in early medieval fortifications. More pertinently, it's an element in a rhetorical move called a "Motte-and-Bailey", originally identified by philosopher Nicholas Shackel. It describes the tendency in discourse for people to move from a controversial but high value claim to a defensible but less exciting one upon any resistance to the former. He likens this to the medieval fortification, where a desirable land (the bailey) is abandoned when in danger for the more easily defended motte. In Shackel's words, "The Motte represents the defensible but undesired propositions to which one retreats when hard pressed."

On The Motte, always attempt to remain inside your defensible territory, even if you are not being pressed.


New post guidelines

If you're posting something that isn't related to the culture war, we encourage you to post a thread for it. A submission statement is highly appreciated, but isn't necessary for text posts or links to largely-text posts such as blogs or news articles; if we're unsure of the value of your post, we might remove it until you add a submission statement. A submission statement is required for non-text sources (videos, podcasts, images).

Culture war posts go in the culture war thread; all links must either include a submission statement or significant commentary. Bare links without those will be removed.

If in doubt, please post it!


Rules


Recommended Posts And Communities

Recommended Realtime Chats