Research Questions Whether LLMs Possess Unique Human-Like Attributes
A preprint posted to arXiv argues that anthropomorphic attributes commonly ascribed to large language models — such as morality or natural language understanding — are not empirically unique to LLMs, demonstrating this by training a neural network on the videogame Age of Empires II. The authors contend that any sufficiently powerful computational substrate, including abstract systems like LEGO or the Greater Boston Area, could exhibit the same purported attributes, and that conclusions about LLM anthropomorphism are therefore substrate-dependent. The paper calls for explicit measurement criteria in AI research and proposes a 'null' assumption of LLM non-uniqueness as a methodological baseline.
Researchers Adrian de Wynter and colleagues have submitted a preprint to arXiv challenging a widespread assumption in AI research: that large language models possess genuinely human-like attributes such as morality or natural language understanding. The paper does not take a position on whether these attributes exist, but argues that current empirical methods cannot establish them as unique to LLMs, because the same behavioral evidence could in principle be produced by other sufficiently powerful substrates. To illustrate this, the authors build and train a simple neural network on Age of Empires II, and further prove that the game is both functionally complete and Turing-complete. They argue that without explicit, substrate-independent measurement criteria, interpretations of LLM behavior are shaped by the representational framing chosen by researchers, leading to either circular or uninformative conclusions regardless of whether the experimenter believes such attributes exist or not. As an alternative, the authors propose adopting a 'null' assumption — treating LLM non-uniqueness as the default — when designing experiments about anthropomorphic properties. The paper is currently in its third revision on arXiv and has not yet undergone formal peer review.
What's missing
The paper is a preprint and has not yet been peer-reviewed, which limits the weight that can be placed on its formal proofs and empirical claims.
What different sources said
- arXiv cs.AICenter
If LLMs Have Human-Like Attributes, Then So Does Age of Empires II
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.