New RFP on Interpretability from Schmidt Sciences

Summary

Request for Proposals Deadline: Tuesday, May 26, 2026 Schmidt Sciences invites proposals for a pilot program in AI interpretability. We seek new methods for detecting and mitigating deceptive behaviors from AI models, such as when models knowingly give misleading or harmful advice to users. If this pilot uncovers signs of meaningful progress, it may unlock a significantly larger investment in this space. Core Question and Overview Can we develop interpretability methods that (1) detect deceptive behaviors exhibited by LLMs and (2) steer their reasoning to eliminate these behaviors? Successful tools will generalize to realistic use cases, moving beyond typical academic benchmarks and addressing concrete risks arising from deceptive behaviors. Importantly, we are looking for interpretability tools that outperform baselines that do not rely on access to weights, to prove that we can truly capitalize on our understanding of model internals. We define a scope of research in the Research Agenda section at the end of this document. Proposals need not match topics in this agenda verbatim. We encourage proposals on any relevant technical methods or evaluation that could advance our scientific understanding of deceptive behavior in LLMs. We will especially focus on three directions: Detecting deceptive behaviors from LLMs: can we develop tools for detecting deceptive behaviors, defined as cases where there is a contradiction between what a model says (or does) and what it internally represents to be true (or the best action)? Steering models to improve truthfulness: can we develop targeted steering methods for intervening on model truthfulness? We would like to leverage better mechanistic understanding of models to develop mitigations for deceptive behaviors. Applications of detection/steering methods: can new detection and steering techniques unlock use cases of AI? When can these techniques improve human-AI teams in practice? When will having more truthful AI improve outcomes from multi-agent systems? Proposal Due Date May 26, 2026 How to apply https://schmidtsciences.smapply.io/prog/2026_interpretability_rfp/ Notification of Decision Summer 2026 Funding Level $300k-$1M (1-3 year projects) Informational Webinars April 2nd, 2026, 1pm ET. Register here April 28th, 2026, 1pm ET. Register here Contact email [email protected] Link to FAQ AI Interpretability FAQ Funding Level and Duration Applicants will be asked in the submission form to give a budget with their proposal that reaches a value between $300k and $1M USD, inclusive of permissible overhead. The application also requires an estimated timeline for the project (one to three years). Project length is independent of total budget, i.e. a one year project could request up to $1M. Budgets should appropriately match resources required for the project. Access to Resources Schmidt Sciences aims to support the compute needs of ambitious and risky AI research. We invite applicants to request the necessary compute resources to achieve the research outputs and outcomes for your proposed project. In the application, you will be asked to describe your compute needs and select between receiving funding or access to Schmidt Sciences’ computing resources. The computing resources offer access to cutting edge GPUs and CPUs, accompanied by large-scale data storage and high-speed networking. Please see the application for more information. Beyond compute resources for your project, Schmidt Sciences offers a wide range of other opportunities for support: Software engineering support through the Virtual Institute for Scientific Software API credits with frontier model providers Opportunities to engage with the program’s research community through convenings and workshops Eligibility We invite individual researchers, research teams, research institutions, and multi-institution collaborations across universities, national laboratories, institutes, and nonprofit research organizations. We are open to applicants globally and encourage collaborations across geographic boundaries. Indirect costs of any project that we fund must be at or below 10% to comply with our policy. Projects funded under this RFP must comply with all applicable law, and may not include lobbying, efforts to influence legislation or political activity. Selection Criteria Proposals will be evaluated by Schmidt Sciences staff and external reviewers using the following criteria: Fit with the Research Agenda. Does the proposal clearly engage with the intention behind the scientific questions and objectives in the research agenda? Scientific Quality and Rigor. Is the proposed work technically sound, well-motivated, and capable of producing generalizable insight? Potential Impact. If successful, would it materially advance AI interpretability or meaningfully change how risks are understood, measured, or managed (ideally through ambitious, field-shaping contributions)? Feas