individual
AI safety fieldbuilding
| Foresight Institute | $150,000 | 100% | 1 |
| Date ↓ | Funder | Via | Amount | Cause | Source | Purpose |
|---|---|---|---|---|---|---|
| Sep 23, 2026 | Foresight Institute | ~$150,000* | AI safety fieldbuilding | foresight | Reinforcement Learning Can Make Latent Private Information More Accessible in Language Models Niloofar Mireshghallah’s group at Carnegie Mellon University, led by CMU student researcher Renfei Zhang, studies how reinforcement learning changes which information language models can retrieve from their parameters. The group trains models with RL and measures when previously latent knowledge becomes easier to retrieve or… — AI for Science & Safety Nodes — 2026 cohort |
* Estimated typical grant size; Foresight Institute did not report grant-level amounts.