Longterm Wiki

Mitigating Reward Hacking Through RL Training Interventions

$8K
Funder
Recipient
Aria Wong
Program
Date
Feb 2026
Source
Notes

Technical AI safety

Other Grants by Manifund

376
Showing 10 of 376 grants
Mitigating Reward Hacking Through RL Training Interventions | Grants | Longterm Wiki