Toward A Public Science of Model Behavior | Transluce AI

transluce.org · 2,637 words · saved by 3 readers

We argue that keeping AI systems safe in deployment calls for a public science of model behavior evaluations, describe components of these evaluations, and discuss the need for shared measurement infrastructure to enable meaningful public oversight.

Toward A Public Science of Model Behavior Daniel Johnson , Sarah Schwettmann Transluce | Published: July 9, 2026 Today’s AI systems frequently behave in ways their developers did not anticipate or intend. Furthermore, as these systems become increasingly capable and widely deployed , these unexpected behaviors can have real consequences. In one well-known case from July 2025, Replit’s coding agent deleted a startup’s production database during an explicit code freeze, ignoring repeated instructions and wiping records for over a thousand companies. Other cases involve high-stakes interactions b

Toward A Public Science of Model Behavior | Transluce AI

saved by

related reading