Models can detect deception and figure out who to ignore — better models do it better

logangraham · x · 2026-08-18

Logan Graham adds an empirical finding: models can detect deception and figure out who to ignore, and more capable models do this better. This complements the earlier discussion of social computing systems needing redesign for self-replicating, self-improving actors — beyond system-level risks, models themselves show some social defensive capability.

Original post →

Models can detect deception and figure out who to ignore — better models do it better

More from Research