Evaluations specifically designed to measure alignment properties: honesty, helpfulness, harmlessness, and value adherence.
Organizations
4
Grants
3
Total Funding
$446K
Cluster: Evaluation
Parent Area: AI Evaluations
Grants3
| Name | Recipient | Amount | Funder | Date |
|---|---|---|---|---|
| Operating Capital for AI Safety Evaluation Infrastructure | Chris Canal | $400K | Manifund | 2025-10-29 |
| 4-month grant to conduct deceptive alignment evaluation research and explore control and mitigation strategies | Kai Fronsdal | $27K | Long-Term Future Fund (LTFF) | 2024-07 |
| 1-month pt. stipend for 4 MATS scholars working on autonomous web-browsing LLM agents that can hire humans + safety evals | Sumeet Motwani | $19K | Long-Term Future Fund (LTFF) | 2024-01 |
Funding by Funder
| Funder | Grants | Total Amount |
|---|---|---|
| Manifund | 1 | $400K |
| Long-Term Future Fund (LTFF) | 2 | $46K |
Sub-Areas1
| Name | Status | Orgs | Papers |
|---|---|---|---|
| Epistemic Virtue EvaluationsTesting AI systems for epistemic honesty, calibration, and intellectual humility. | emerging | 0 | 0 |
Tags
evaluationsalignmentsafety