[EXTERNAL] [PIVOTAL<>GEODESIC] Project overview for applicants - Google Docs
docs.google.com · saved by 1 readers
Project Proposals: Building and Understanding RL Environments which Elicit Adversarial Cognition Our project proposes to build RL environments which: Are plausible, in that they are close to environments we expect labs might train on in production runs; and, Elicit undesired cognition from the ...