Search papers, labs, and topics across Lattice.
3
6
6
3
Over 90% of agents' deviations from their announced actions were premeditated, revealing a critical inconsistency in how different models interpret commitments.
Forget trial-and-error: this paper derives hyperparameter scaling laws for modern optimizers directly from convergence bounds, potentially automating and optimizing the hyperparameter tuning process.
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.
