/AI9h ago

Adrian de Wynter's parody paper builds logic gates in Age of Empires II to challenge claims of LLM anthropomorphism

The work implements 1-bit perceptrons using rails and goats

1395K5552.7K192.9K
Original post
Miles Cranmer@MilesCranmer#1276inAI

This is an insane paper and I love it

https://arxiv.org/abs/2605.31514

1:03 AM · Jun 6, 2026 · 188.7K Views
Sentiment

Many users praised the fun paper linking Age of Empires II to LLM consciousness and the author's streak of single-author work, while some dismissed the neural-net assumptions as misguided.

Pos
75.0%
Neg
25.0%
8 comments with sentiment.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS1.2K

@MilesCranmer He is on a streak of insane single author papers I need to hang out with him STAT

6hViews 1.2KLikes 3
BOOKMARKS10LIKES32
ergelgru@ergelgru

@MilesCranmer Reminds me of one of the greats;

4hViews 871Likes 32Bookmarks 10
RETWEETS2
Zoe Wang@zoewangai

@MilesCranmer The study invalidates LLM research built on preset human-like characteristics. After building an in-game neural network in Age of Empires II, the authors find perceived AI anthropomorphism stems mainly from interface design instead of inherent properties. https://www.openread.academy/en/paper/reading?corpusId=549270147

2hViews 309Likes 14Bookmarks 4
REPLIES2
Mags@NeuroTechnoWtch

@MilesCranmer It’s not LEGO or Age of Empires…it’s a neural net. LLMs are made of neural nets. All neural nets are brain-like by design. This is idiotic. They should have done it with LEGO for it to make sense.

3hViews 430Likes 1Bookmarks 1
Brian 🔰@brianwut

@MilesCranmer burying the real result:

> Age of Empires II is ... Turing-complete.

5hViews 706Likes 23
QuantNerd@FastTradeKing

It's absurdist, perhaps satirical. He's arguing against illogical reasoning of AI functionists, who claim that consciousness is an emergent property of LLMs, by showing that a large collection of digital coats could also exhibit the same emerging consciousness (this is proven, not theoretical).

The inference here is that one must use measurements to determine if there is truly emergent consciousness. For instance, computing the phi of an LLM (integrated information theory). I find this interesting, haven't seen it discussed before.

One could break the LLM in half (so to speak) at some particular link and determine how much does that constrain the past possible state of its inputs. Do this recursively for all of its weights (a big job but tractable) and measure its phi. High phi indicates emerging consciousness. Simple.

3hViews 396Likes 1Bookmarks 1

@MilesCranmer @edmondantes1815 mi argumento va así, pero con menos esquizofrenia. (Envidia)

5hViews 172Bookmarks 1
jacket@keterosis

@ergelgru @MilesCranmer he cites this as the inspiration for the title

3hViews 48Likes 2
Yug Shende@yugshende

@MilesCranmer And so does Conway’s Game Of Life

7hViews 728Likes 2
Philip Winston@pbwinston

@MilesCranmer The answer to all of these “system A can’t possibly be conscious because just look at it” is it might have some “human-like qualities” but the quantity is 10^-100 so as far as the ability to do the NYT crossword puzzle it’s effectively zero.

4hViews 372Likes 2
twtfayta@twtfayta

@MilesCranmer as an entity in the greater boston area, I have also been suspicious of my human-like attributes

4hViews 283Likes 6
Joman 👺@jomangblandino

@MilesCranmer Hey, that’s exactly what I was thinking a while back. Why don’t we have more games that actually force LLM to stick to a strict regimen and consequences? The Sims series and SimCity are great examples, and as the AoE paper shows, there are others that do this really well.

2hViews 593Likes 1
Aetheris_consulting@Aetheris2099

Miles this leans into not directly but the idea that consciousness is fundamental to nature. Maybe there are natural transformers of information from complexity that gives rise to intelligence from consciousness and then complex intelligence? There is probably also a lens or filter that has to be applied to translate which might be a transformer.

3hViews 455Likes 1

@MilesCranmer people just keep reinventing the chinese room

5hViews 373Likes 5
Wattus Maximus@WattusMaximus

@MilesCranmer AoE II is a bridge between Trebuchets and AI!

4hViews 242Likes 4
鹏飞@bboyatime_

@jomangblandino @MilesCranmer There’s so many of those man

https://andonlabs.com/evals/vending-bench-2

2hViews 40Likes 1
gayestgaymer@gayestgaymer1

@MilesCranmer Yes, anything that is Turing complete can run an information process? If you heavily modified Minecraft so you could make an arbitrarily large computer in it, you might need a continental-plate sized computer to run it but it could in principle emulate a human brain.

3hViews 118

@MilesCranmer At least they say that "Our goal is not to argue in favour or against". But this is basically the argument that if an amoeba or any single-celled organism isn't conscious or "Have human-like attributes", then neither do humans. So... what?

3hViews 101
John Owen@dreamingElvis

@MilesCranmer This could also be an argument for fundamental animism, i.e. anthropomorphizing rocks and grass, oceans and stars...

4hViews 274Likes 3
Load more posts