Research on detecting when AI systems are engaged in deceptive alignment or strategic manipulation of their training process.
Organizations
4
Grants
1
Total Funding
$27K
Cluster: Evaluation
Parent Area: AI Evaluations
Grants1
| Name | Recipient | Amount | Funder | Date |
|---|---|---|---|---|
| 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 |
Funding by Funder
| Funder | Grants | Total Amount |
|---|---|---|
| Long-Term Future Fund (LTFF) | 1 | $27K |
Tags
evaluationsdeceptiondeceptive-alignment