Loading activity…
@ancadianadragan
Google DeepMind • AI safety & alignment • model behavior • associate professor @ UC Berkeley EECS
AI
A post argues that human tasks are now too easy to use as AI benchmarks in many domains.
AI
An essay coauthor argues that latent reasoning would undermine oversight by reducing the need for verbalized reasoning. A reply disputes any further loss of oversight, arguing that reinforcement learning already makes reasoning tokens uninterpretable.
AI
An essay coauthor challenges the idea that chain-of-thought reasoning will inevitably disappear, arguing that model designers can choose to preserve its monitorability.
