Schmidt Sciences logo
Science of Trustworthy AI

AI Interpretability RFP

Funds mechanistic interpretability research on detecting and steering deceptive behaviors in artificial intelligence systems.

ClosedSchmidt SciencesUnited States

The 2026 AI Interpretability RFP, issued by Schmidt Sciences under its Science of Trustworthy AI program family, funded research on detecting and correcting deceptive behaviors in AI systems. Schmidt Sciences defined deceptive behaviors to include factually incorrect statements, misleading confidence claims, fabrications, selective omission, evasiveness, and false claims regarding a model's self-k…

Mechanistic interpretability research on detecting and steering deceptive behaviors in AI models, and translating those methods into practical human-AI collaboration and multi-agent applications.

CycleiHow often this grant runs — e.g. annually, on a rolling basis, or a one-off call.Annual
Next deadlineiThe next date applications are due. Rolling means you can apply any time.—
Decision timeiTypical time from the deadline to the funder's decision.—
Project durationiHow long the funded work is expected to run.12–36 months
Award typeiThe form of funding — grant, equity, loan, tax credit, etc.Grant
Match fundingiThe share of project costs you must cover yourself. 0% = fully funded.0%
Funding pooliThe total budget available across all awards in this round.—

Sign up free to see the funding breakdown

Sign up free to see the industries in scope

Sign up free to see the full eligibility

Sign up free to see how to apply

Sign up free to see the timeline

Last verified: 22 Jul 2026Source: schmidtsciences.smapply.io