one dataset · paper, tables, graph, wiki
simgrammar the grammar of simulation

locator

https://www.nso-journal.org/10.1360/nso/20250053

notes

With task instructions removed or replaced by misleading ones, Centaur still generally outperformed domain-specific cognitive models; authors conclude it relies on superficial statistical cues rather than understanding instructions.

cited by

1 records

LLM models of individual human choice

provenance

runs in log/runs
2026-10-24
created2026-10-24-techniques-llm-agentstechnique