Research Questions Whether LLMs Possess Unique Human-Like Attributes
A new arXiv paper argues that claims about large language models possessing human-like attributes (such as morality or understanding) may be unfounded, demonstrating that simpler systems like the video game Age of Empires II could exhibit similar properties. The researchers contend that attributing anthropomorphic qualities to LLMs requires explicit measurement criteria rather than relying on interpretation of observed behavior. The work challenges a widespread assumption in AI research and proposes a methodological framework for more rigorous evaluation of such claims.
Researchers have published a preprint arguing that many studies attributing human-like attributes to large language models—such as morality, understanding, or reasoning—may be drawing incorrect conclusions. To support this critique, they trained a simple neural network on the video game Age of Empires II and demonstrated that various substrates (including LEGO or physical locations) could theoretically exhibit similar apparent attributes. The authors emphasize that while some LLM properties like prompt responses may remain consistent across different interpretations, the meaning assigned to observed behavior is substrate-dependent. They argue that without explicit, measurable criteria, conclusions about anthropomorphic attributes in LLMs are fundamentally interpretive rather than empirically grounded. The paper proposes a methodological approach based on assuming LLM non-uniqueness rather than assuming anthropomorphic attributes exist, and includes a proof that Age of Empires II is Turing-complete.
What different sources said
- arXiv cs.AICenter
If LLMs Have Human-Like Attributes, Then So Does Age of Empires II
Related
Topology-Aware Thermodynamics Improves DNA Probe Specificity Design
Researchers developed a new framework for designing DNA probes that accounts for the spatial organization of matched sequences, not just overall thermodynamic stability. Traditional methods rely on scalar measures like melting temperature and free energy, which miss how mismatches are distributed along the probe. The approach could improve diagnostic accuracy in applications like HPV detection and gene expression profiling.
Study Identifies Optimal Thermal Dose for Combining Focused Ultrasound with Immunotherapy in Tumors
Researchers used multimodal PET imaging to identify an optimal thermal dose range for focused ultrasound ablation that destroys tumor tissue while preserving conditions for immunotherapy delivery. The study found that excessive heating collapses blood vessels needed for antibody access, while insufficient heating fails to adequately reduce tumor burden. The findings could guide clinical design of combination treatments pairing thermal ablation with immunotherapies.
Plant MSH1 Protein Functions as Mismatch-Directed Nuclease for Organelle Genome Maintenance
Researchers have identified the precise mechanism by which the AtMSH1 protein in Arabidopsis plants recognizes and cleaves DNA mismatches and lesions, preventing mutations in organellar genomes. The protein combines a DNA mismatch recognition module with a nuclease domain that makes staggered cuts at specific positions relative to DNA damage. This discovery explains how plants maintain unusually low mutation rates in their mitochondrial and chloroplast DNA compared to other eukaryotes.