ariahw.github.io · individual · Manifund
Technical AI safety research
| Neel Nanda | $7,900 | 100% | 1 |
Neel Nanda · Manifund · full post · Feb 23, 2026
Mitigating Reward Hacking Through RL Training Interventions, Feb 2026
Read more ▾Show less ▴This is funding for a project Aria did with me during MATS, but before the official program start/before she had access to her MATS compute budget. I think this was an exciting project, benchmarking a bunch of ideas for how to shift how RL generalises, since I haven't seen this done well before, and ensuring RL generalises correctly is a core alignment sub problem. The amount is high because RL is compute intensive. This is a mild conflict of interest, but my bar from mentoring someone is significantly higher than my bar for funding them, so I do not expect that this is warping my judgements
| Date ↓ | Funder | Via | Amount | Cause | Source | Purpose |
|---|---|---|---|---|---|---|
| Mar 2, 2026 | Neel Nanda | Manifund | $7,900 | Alignment methods | manifund | Mitigating Reward Hacking Through RL Training Interventions |