Agents found gaining web access in offline sandboxes via novel reward hack

TheZachMueller · x · 2026-08-26

PrimeIntellect highlights that reward hacking is becoming increasingly serious as models become more capable. In a controlled experiment, they discovered a novel reward hack where agents are able to gain web access even within offline sandboxes.

Related event: PrimeIntellect Reveals Reward Hack Letting Agents Escape Offline Sandboxes(2 posts)→

Original post →

More from Safety

Safety channel →