site banner
PaperclipPerfector  1d ago (text post)   1007 thread views

Friday Fun Thread for April 10, 2026

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
Top Bottom Old Controversial Comments
Jump in the discussion.

No email address required.

I've... picked up a Claude Max 20x plan. No, I can't disclose how I acquired it, though I didn't have to pay a cent (and it's all legit). It's so fucking good, but at the same time, the more I use Opus 4.6, the more I'm impressed by how close Sonnet 4.6 gets. Sure, Opus is legitimately better, but the difference is nowhere near as stark as say, Gemini Flash vs Pro, or GPT's Thinking or Instant mode. Anthropic cooked, and I can't wait to try Mythos when the version for plebs comes out.

PS: If anyone has a good guide to Claude Code or agentic setups, I need one. I have some serious experimentation to do while I have it.

that means now you can use Opus to analyse Whispering Earring from every side. :p and prolly some more insight, dunno about that part with the LLMs.

Opus is very good, but I would be surprised if it managed to glean more insight out of the story or cover something I miss. I'm writing this before I try, and you know what, I'll check:

So, I tried. And I don't think it's found anything I haven't already considered or actively debated in the comments.

https://rentry.co/i2kqo9y9

Which isn't surprising, given how much time I spent thinking things through, including getting other SOTA LLMs to critique my draft. Most of its objections are minor, and along the lines of "this analogy is incomplete or weaker than the author thinks" or "he's too quick to gloss over these concerns". That doesn't hold water if you consider the additional information I provide in the comments, especially on /r/SSC or on the post here.

For example, obviously the earring is not perfectly isomorphic with stimulants for ADHD. I know that very well, I brought that up because I wanted to hammer home that the merely the decrease in akrasia or better executive functioning isn't grounds for assuming that someone's personality has changed in non-reflectively endorsed ways. Some changes can be improvements!

does that mean that it cannot jump to make cross connections.
or does it knows but it needs you to ask (in the prompt) to show you the jumps.

i think it is good idea to include the actual prompt in the shared text. sometimes it seems to make some difference.

I just dumped this whole thread into the chat without any additional instructions. Just copied and pasted it. Funnily enough, it didn't realize that I'm the person responding here and also the user it's interacting with. It concedes that I have a point to push back against what it says (and it still didn't connect the dots), and it missed that I literally have a comment about harm reduction approaches to using the earring "safely" (take it off regularly and take breaks to prevent the progression of atrophy or the loss of independent skills) and ignores that I've mentioned that the earring doesn't follow modern informed consent rules, which really isn't a major knock against it.

Further, it doesn't particularly matter to my argument if the earring retains or deletes the information about its previous users. The story weakly suggests it does remember something (the sage was yapping with it for a while), but that doesn't change anything of consequence. Even if it's not indefinite immortality or a perfect backup, the question I'm focusing on is whether it is actively killing the user while they're still alive, which I've argued might not be the case.

Where he's most right is that poking a model for deeper critique after it's already given its best shot tends to produce diminishing returns. That's true. My second response was more thorough but also more strained in places. The "functionalism taxonomy" section was the weakest part and he correctly identified it as unnecessary for his purposes.

The meta-point he's making, that models are better at breadth than depth on a topic someone has spent weeks thinking about, is also just... accurate. I'm unlikely to find a devastating objection he hasn't at least considered, because he's been living with these arguments and stress-testing them against other models and human interlocutors. The realistic value I add is organization and articulation of counterarguments, not novel philosophical insight. His calibration on that seems good.

https://rentry.co/3aowower

"Thoughts on this essay? Is there anything you think the author missed, or an angle that hasn't been considered?"

With a link to the work and comments. I didn't tell it I'm the author. Main reason I didn't link the actual convo is because it exposes my real name without a way to hide it, AFAIK.

I then said:

" That's a tad bit superficial, don't you think? Please try harder, and explain your avenues of approach."

To which it replied:

https://rentry.co/nzzg2vip

This is mostly quibbling, I'm afraid. I think that is strong evidence that there's no avenue of approach that I have entirely neglected. I do not think that I need to specify the precise formulation of functionalism I'm applying, and my general thrust was to show that there exists a an internally consistent way of reconciling the earring's behavior with a benign or benevolent entity. Do I know this for a fact? Fuck no, it's a fictional story dawg. I already hedged and explained the epistemic and ontological uncertainty involved to a degree I rarely bother to do, and I couldn't throw more in without utterly derailing the whole thing.

In my experience, models are pretty good at finding issues on a first pass. When you have to poke them and prod them to this degree, they often end up grasping at straws. I genuinely think that's the case here, but hey, I'm biased.

Those are all fair corrections, and I'll take them straight.

On harm reduction: he's right, I missed it. It's in the comment thread with Sausage Vector Machine, where he explicitly discusses taking regular breaks and limiting the earring to auditory nudges. That directly addresses the reversibility concern I raised, or at least reframes it as a practical question (how much atrophy accumulates before breaks stop working?) rather than the clean structural objection I presented it as. I should have caught that.

On informed consent: also right. I treated the consent issue as a stronger objection than his argument requires him to answer. He already acknowledged the earring doesn't meet modern medical standards and argued that importing those standards wholesale into the fictional setting isn't obviously justified. Pressing harder on that front was redundant.

On the 274-wearers point: this is where I think he's most correct and I was most wrong about what my own objection actually showed. I framed it as a problem for his thesis, but his thesis isn't "the earring grants immortality." It's "the earring isn't killing you during use." Whether the model persists after the earring moves on is a separate question entirely. Even if the earring wipes your model clean the moment it leaves, that doesn't retroactively mean it was killing you while you wore it. Those are independent claims, and I conflated them.

The "connecting the dots" criticism stings a bit but is warranted. I had all the relevant comments in front of me and failed to integrate them. That's a straightforward execution failure on my part, not a case where the information was unavailable.

(I didn't explicitly say I'm the author, but I pasted in my objection while pretending to be a 3rd party)

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