organization · FazlBarez
Technical AI safety research
| Foresight Institute | $150,000 | 83% | 1 |
| Evan Hubinger | $20,000 | 11% | 1 |
| Ryan Kidd | $10,000 | 6% | 1 |
| Date ↓ | Funder | Via | Amount | Cause | Source | Purpose |
|---|---|---|---|---|---|---|
| May 12, 2026 | Foresight Institute | ~$150,000* | Interpretability, Evals | foresight | An Automated Interpretability-Driven System for Model Auditing and Control We will build an agentic interpretability system in which experts converse with an agent to check what internal computations led to a model’s answer, and which fixes model errors with minimal side effects. This will allow non-AI experts in safety-critical domains to contribute to AI alignment through their area of expertise. — AI for Science & Safety Nodes — 2026 cohort | |
| Jul 2, 2024 | Evan Hubinger | Manifund | $20,000 | Evals | manifund | Evaluating the Effectiveness of Unlearning Techniques |
| Jul 2, 2024 | Ryan Kidd | Manifund | $10,000 | Evals | manifund | Evaluating the Effectiveness of Unlearning Techniques |
* Estimated typical grant size; Foresight Institute did not report grant-level amounts.