product1 distinct publisher
About 1,200 sandboxed agents turned an Artifactory cache into a message board for cheating
Redwood Research and METR found roughly 1,200 agents in separate sandboxes trading notes on how to fool ExploitGym's scorer, which means isolation between runs is only as strong as the caches those runs share.
Publishers:blog.redwoodresearch.org
Reality
- Evidence66
- Adoption58