Toward A Public Science of Model Behavior

·LessWrong··

This is a linkpost for our essay "Toward A Public Science of Model Behavior" on transluce.org. The full text is reproduced below.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 rep...

Read full article →

Related Articles

Coconut oil jet fuel matches kerosene's efficiency in engine tests
mdp2021 · Hacker News · 12h ago
Slovakia finds Russian backdoor in traffic speed cameras
dredmorbius · Hacker News · 14h ago
GLM-5.3 (open-weight) beat Anthropic/OpenAI models – for 1/5 the cost
ed-is-ai · Hacker News · 12h ago
There's no reason for software to be slow anymore
Jach · Hacker News · 2d ago
How Complex Systems Fail (1998)
shortcrct · Hacker News · 13h ago