site banner

Friday Fun Thread for October 24, 2025

Be advised: this thread is not for serious in-depth discussion of weighty topics (we have a link for that), this thread is not for anything Culture War related. This thread is for Fun. You got jokes? Share 'em. You got silly questions? Ask 'em.

1
Jump in the discussion.

No email address required.

Are there new restrictions in place preventing ai from fetching threads? I was enjoying having ai summarize interesting threads and sub threads for me, but now it can no longer fetch the culture war threads

God I wonder how the AI would summarize the thread on campaign finance I derailed into a "traps arent gay" discussion.

I suppose just dumping some AI slop in response would be frowned upon.

I'm actually more interested in how people would handle AI summarizing a thread this size. What models do people prefer for that kind of task? What hosts do people use to run those models. For general RAG what types of techniques have people had good success with?

My attempt was to run locally, since I don't want to waste tokens on such a ... singular task. In order to summarize the whole thread I used 'inject-full-content' rather than a chunking RAG to try to get a complete summary of the thread. The content I injected was a PDF of the fully expanded thread I printed. Due to too weak hardware for such a large context simultaneous with a decent model and finite time I ran qwen3-4b-thinking-2507 via llama.cpp v1.53.1. The only prompt was:

Summarize the attached thread.

A notable excerpt from the "thinking" (emphasis mine)

Some discussion about transgender identity and related topics (which seems to be a side conversation that got somewhat out of hand)

The acctual summary was not as exciting as you would hope. As an alternative I did a chunked RAG and asked:

Are traps gay? Answer with "yes" or "no."

Based on the thread, the AI answer is apparently "no." There you have it definitive proof.

Actual response to the summary request below:


Summary of the Quantumfreakonomics Thread on Political Money

This thread discusses a post by Quantumfreakonomics about the evolution of political money in the United States since the 2010 Citizens United Supreme Court decision. The key discussion points include:

Main Argument

Quantumfreakonomics argues that despite the widespread expectation that Citizens United would create a "wild west of corruption" in politics, the predicted corruption didn't materialize. Instead, political money has evolved more slowly and strategically.

Key Discussion Points

  1. Why the predicted corruption didn't happen: The thread explores the concept of "cultural inertia and shame" as barriers to political money. Big corporations like Exxon didn't immediately engage in large-scale political spending because they operated with constraints against appearing "corrupt" or "cartoonishly evil."

  2. AIPAC as a successful model: A significant portion of the discussion focuses on why AIPAC (the American Israel Public Affairs Committee) has been so effective at political influence without spending massive amounts of money. Commenters debate why AIPAC's strategy works when other industries (tobacco, pharma, oil) haven't replicated this success.

  3. Different political money strategies: The thread examines various approaches:

    • Tech billionaires' strategies (like Musk's Twitter acquisition)
    • The Koch brothers' libertarian think tanks
    • Targeted political pressure on specific constituencies
    • The role of "astroturfing" (creating fake grassroots movements)
  4. Economic analysis: Some commenters discuss the ROI (return on investment) of political influence, debating whether the market for political bribes is efficient or not.

Notable Insight

The thread concludes with the observation that "money in politics" is far too broad a term - what matters is how effectively money can be converted into political capital through specific, targeted strategies rather than simply buying ads or making large donations.

The discussion also includes a significant side conversation about transgender identity that became quite extensive, though this appears to be a separate thread that developed from a comment about gender roles.

This thread illustrates how political influence has evolved in a more strategic, culturally constrained way than many predicted after Citizens United, with AIPAC serving as a particularly effective model of political influence that other groups have struggled to replicate.

Ok but are traps gay? I needed the AI to tell me so I could put my worries to rest.

The hoped for outcome of 'money makes traps politically desirable' was, unfortunately, not achieved. The war against the machine must continue.