Matt Pearce
@mattdpearce.com
56K followers 1.4K following 2.2K posts
May the forces of evil become confused on the way to your house. Opinions are my own (but they are correct) mattdpearce.substack.com
May the forces of evil become confused on the way to your house. Opinions are my own (but they are correct) mattdpearce.substack.com
![[Submitted on 29 May 2026 (v1), last revised 11 Jun 2026 (this version, v3)]| If LLMs Have Human-Like Attributes, Then So Does Age of Empires Il
Adrian de Wynter
View PDF
Much research has been carried out on large language models (LLMs) and LLM-powered agentic workflows.
However, many works within the field state emergence of, ascribe to, or assume, generalised anthropomorphic attributes to them (e.g., morality or understanding of natural language). Our goal is not to argue in favour or against the existence of these attributes, but to point out that these conclusions could be incorrect. For this we build and train a simple neural network on the videogame Age of Empires II, and note that any entity in a sufficiently-powerful substrate, such as LEGO or the Greater Boston Area, could also present such attributes. Hence, the purported anthropomorphic attributes of LLMs are empirically non-unique: although some properties (e.g., responses to prompts) could remain invariant, others, such as the interpretation of their perceived behaviour, might change with the substrate. Thus, any empirically-grounded discussion on these attributes requires explicit measurement criteria; otherwise the interpretation is left to the representation. We then show that assuming that these attributes exist or not in a system, independent of the substrate and in a generalised way, leads to either circular or uninformative conclusions. This is regardless of the experimenter's viewpoint on the subject, or whether the outcome shows existence or non-existence. Finally we propose a 'null' assumption, where one assumes LLM non-uniqueness instead of assuming anthropomorphic attributes to set up an experiment, along with examples of it. We also discuss potential objections to our work, briefly survey the field, and prove that Age of Empires Il is functionally- and Turing-complete.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:qvyj3hxm4opuuddzrhcbiio6/bafkreibcrjs6fyua3w4pbtu4axyvpalvxqou4bxkovqiwwcowiel4yzwca)
![When the Dred Scott decision said that the Constitution applied only to free subjects in the eighteenth century, Lincoln took Douglas's defense of that position and did another of his word substitutions, to reduce his opponent to absurdity:
Suppose after you read it the Declaration of Independence] in the old-fashioned way, you read it once more with Judge Douglas' version. It will run thus: "We hold these truths to be self-evident, that all British subjects who were on this continent eighty-one years ago, were created equal to all British subjects born and then residing in Great Britain." [SW 1.400]
Parker had made a similar substitution in 1848: "To make our theory accord with our practice, we ought to recommit the Declaration to the hands which drafted that great state paper and declare that 'All men are created equal, and endowed by their Creator with certain unalienable rights if born of white mothers; but if not, not.' »36](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:qvyj3hxm4opuuddzrhcbiio6/bafkreid7hmxh5v6d6op7vm3wi4nvz3gql26bys6as6wkoyrm7an5x22e6a)
