2026-10-01 · paper-digest
Lessard et al.: Can a Machine Dig the Good Stories Out of a Simulation? — Fukai Reads
A paper by Jonathan Lessard and colleagues on emergent narrative. They tried to automatically pick 'interesting stories' out of 228K events produced by a social simulation, using 'unexpectedness' and 'dramatic situations' as heuristics, and had 24 readers rate the results. The clear favorite turned out to be the control story, chosen with no heuristic at all.
