The BaseEssayLessWrong
Anthropomorphic vs Biological reasoning for thinking about human analogies for LLM behavior
According to the excerpt, mcnairs argues on LessWrong that the debate over whether to reason about AI models anthropomorphically is a false dichotomy, and distinguishes two separate sources of human analogies for model behaviour: 'anthropomorphic' reasoning and what the author calls 'biological' reasoning.
Why it matters
The same thing, for different readers.
For researchers
mcnairs offers a way to separate two kinds of human analogy when predicting model behaviour, with more falsifiable predictions promised in a later post.
The question it raises
mcnairs questions whether comparing AI models to humans must mean assuming human-like minds, by separating two different grounds for the comparison.
The record
- Questions
- What values should AI have, and could it have a mind of its own? · Can AI systems act beyond what people intended or allowed?
- People
- mcnairs (Wrote it)
- What we read
- We have read only the description the publisher gives. No quotations until someone reads the source itself.
- Found by
- The Radar, run of November 2, 2026, via
lesswrong(tier 1: the source’s own channel or an official record) - Cite this
- LessWrong, “Anthropomorphic vs Biological reasoning for thinking about human analogies for LLM behavior”, November 1, 2026. Entry in the Ctrl AI Base, https://ctrlai.com/base/lesswrong-2026-11-01-anthropomorphic-vs-biological-reasoning
Our notesLight lane: written from the triage excerpt only; the definition of 'biological' reasoning was cut off. Author known only by forum handle.