What a crowdsourced game revealed about steering Olmo 3

Allen Institute for AI Version 1 original current

Imported from official source

A crowdsourced game built on Olmo 3 showed how people can exploit unexpected model behaviors to stress-test prosocial AI evaluations—and how open access to a model’s internals can help researchers understand why those tests break.

This version

Version
1 of 1
Recorded
September 20, 2026 19:52
Change
Initial
Content hash
beaaab0ca8846856d2c1a9393c924101
All versions
Revision history

Officially records where a publication came from, not whether it is true. Imported records are reproduced from an organization's own official source.