Tracking AI existential risk. Source-backed context. Original reporting always linked.
MONITORING CORE AI-RISK FEEDS · UPDATED HOURLY
Research

Metagaming matters for training, evaluation, and oversight

Zac Boring March 18, 2026 1 min read
Read original source →

Following up on our previous work on verbalized eval awareness:we are sharing a post investigating the emergence of metagaming reasoning in a frontier training run.Metagaming is a more general, and in our experience a more useful concept, than evaluation awareness.It arises in frontier training runs and does not require training on honeypot environments.Verbalization of metagaming can go down over the course of training.We also share some quantitative analyses, qualitative examples, and upcoming

By jenny

Read the full article at Alignment Forum →