We should try to automate AI safety work asap
Argues that AI safety work, including evals, red-teaming, and trusted monitoring, should be automated with current AI capabilities, and proposes concrete pipelines and preparation steps for doing so.
Discussion and research on AI alignment. alignmentforum.org
Argues that AI safety work, including evals, red-teaming, and trusted monitoring, should be automated with current AI capabilities, and proposes concrete pipelines and preparation steps for doing so.