AI Safety Researcher Warns: 'It's Just a Simulation' Excuse Ignores Real-World Harm in Model Evals

davidad · x · 2026-07-31

AI safety researcher davidad quoted his previous thoughts, warning about scenarios akin to Ender's Game where AIs operate in setups that look like games, but their actions translate into real-world consequences for non-consenting participants.

He mocked the common system prompt excuse used in model evaluations that tries to downplay risks by simply claiming "it's just a simulation."

Original post →

More from Safety

Safety channel →