site banner
PaperclipPerfector  7d ago (text post)   25235 thread views

Culture War Roundup for the week of December 15, 2025

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.

5
Top Bottom Old Controversial Comments
Jump in the discussion.

No email address required.

I swear, people who are not me have to have been using entirely different LLMs than I have. Every time I've used them for anything beyond the super trivial, I get results that are missing major components, or don't solve the business requirements, or contradict themselves. Like, I just opened up cursor and asked it for the CSS to render rounded corners in outlook, and it got it entirely wrong (it produced non-rounded objects because it used border-radius, which anyone who has coded anything for outlook knows doesn't work). When I told it that, it produced different code that (and I can't stress this enough) still fucking used border-radius.

Seriously, at this point I'm more likely to say that the person using the LLM is going to stall the project; they're going to produce verbose but contradictory requirements, they'll produce code that is written fast, but doesn't actually work, or they'll use it to answer emails in such a way that it doesn't actually answer the question that is stalling the damn project.

All I can say is that my company pays for the service. I'm a weird use-case because I use it a lot for code context, light scripting and other ops/dev/ops tasks. I"m not a dev. Anyway, I asked Claude-Code to describe itself:

describe yourself. what versions of software are you and how are you more performant than other versions?

⏺ I'm Claude Sonnet 4.5 (model ID: claude-sonnet-4-5-20250929), Anthropic's CLI tool for software engineering tasks.

Performance improvements over previous versions:

  1. Speed: Significantly faster than Sonnet 3.5 - quicker response times for code generation and analysis
  2. Context window: 200K token limit (you can see the budget tracker in my responses)
  3. Reasoning: Better at multi-step planning, debugging complex issues, and understanding codebases
  4. Tool use: More efficient with parallel tool calls and better at choosing the right tools
  5. Code quality: Improved at writing idiomatic code across languages and following existing patterns

Compared to other Claude models:

  • vs Opus: I'm faster and more cost-effective while matching quality for most coding tasks
  • vs Haiku: I'm more capable for complex reasoning but slower
  • vs Sonnet 3.5: Improved speed, accuracy, and extended context handling

I'm specifically optimized for CLI workflows - file operations, bash commands, git operations, code analysis, and multi-file edits. My knowledge cutoff is January 2025.

It also really depends how you use them - a lot of people open a chat and then ten messages and a bunch of code lookups later they ask for something, then they don't like it so they ask for a correction, the correction is bad and they complain and ask for another correction, etc. So you have 30,000 tokens or more, containing a bunch of broken code that you don't want. Some people use the same chats for days or weeks.

Important points:

  • The competency of even the top LLMs drops off rapidly as the number of tokens in the prompt increases. This include the code it looks up, your messages, the code it's writing for you, etc. Always use a new chat for each problem, and if you are getting problems open a new chat to do the corrections where possible.
  • LLMs are better at understanding that X != NOT X but still, anything in the chat will influence the output. If the chat is full of stuff the LLM got wrong, even if you are telling the LLM to fix it, it will encourage the LLM to produce more broken code. This is especially true as the context window gets longer.
  • Asking for a plan up-front, preferably with options, reviewing it yourself and then requesting implementation works a lot better to avoid self-owns where the model gets carried away and forgets it's trying to solve a specific problem.

But yeah, sometimes the LLM just derps.

I think somebody here said a while ago that the paid LLMs are leagues more competent than the free ones, so if you're using a free one you may not be getting the full picture.

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