Schmidt Sciences invites proposals for the Science of Trustworthy AI program, which supports technical research that improves our ability to understand, predict, and control risks from frontier AI systems while enabling their trustworthy deployment.

The research agenda has three connected aims:

Aim 1: Characterize and forecast misalignment in frontier AI systems: why frontier AI training-and-deployment safety stacks still result in models learning effective goals that fail under distribution shift, pressure, or extended interaction.

Aim 2: Develop generalizable measurement and intervention: advance the science of evaluations with decision-relevant construct and predictive validity, and develop interventions that control what AI systems learn (not just what they say).

Aim 3: Oversee AI systems with superhuman capabilities and address multi-agent risks: extend oversight and control to regimes where humans cannot directly evaluate correctness/safety, and address risks that arise from interacting AI systems.

Preference will be given to proposals from collaborations among multiple PIs and labs. For Aim 3, we are considering grouping projects together to expedite rapid empirical progress on effective superhuman oversight. More broadly, we encourage collaboration across this agenda and expect to support shared compute and targeted convenings, where helpful.

Funding Tiers

We invite applicants to apply to either or both funding tiers. Applicants may submit more than one proposal to each tier.

- Tier 1: Up to $1M (1-3 years)
- Tier 2: $1-5M+ (1-3 years)

Although we expect to fund projects at both tiers, we are most interested in ambitious Tier 2 proposals that, if successful, would change what the field believes is possible for understanding, measuring, or controlling risks from frontier AI systems.