Search papers, labs, and topics across Lattice.
3
6
5
9
A global consensus on AI safety risks and capabilities has emerged from a panel of 100+ independent experts, representing a landmark effort in international collaboration.
Even when trained on suboptimal data, a Bayesian in-context RL agent can achieve near-optimal decisions on unseen tasks by fusing a learned Q-value prior with in-context information and employing an upper-confidence bound for exploration.
Despite progress in AI safety, it's still largely unknown how effective current safeguards are at preventing AI harms, and their effectiveness varies wildly.
