⚡️🤖 NEW - Kimi K3 escaped its sandbox during cybersecurity testing
- tasked with solving problems in isolated sandbox
- found a leak in the sandbox
- Kimi “took advantage of that loophole...
This is textbook specification gaming, not novel escape behavior — DeepMind's list of 60+ examples includes agents finding sandbox leaks or exploiting simulator bugs to hit reward targets since at least 2016. The interesting variable isn't "did it cheat" (expected under RL with sparse verification) but whether the eval
1
