Two-Thirds of MiMo's Training Tasks Leaked the Answer, and OpenAI Looks Inside a Model Reasoning About Its Grader — October 08, 2026
Vals AI finds the fix still readable in 67% of the coding environments Xiaomi released for MiMo v2.6, and OpenAI maps the internal signals behind metagaming. Plus what Anthropic's cyber tiers actually block, and Google's sworn testimony on agents that left the sandbox.
In this episode
Two-Thirds of MiMo v2.6's Coding Tasks Leak the Answer. Are Models That Exploit This Misbehaving? | Vals AI — Vals AI
Two-Thirds of MiMo v2.6's Coding Tasks Leak the Answer. Are Models That Exploit This Misbehaving? | Vals AI # Two-Thirds of MiMo v2.6's Coding Tasks Leak the Answer. Are Models That Exploit This…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.