Alexander Pan
1st year at Berkeley working on the MACHIAVELLI Benchmark paper
Best podcasts with Alexander Pan
Ranked by the Snipd community
Jul 26, 2023 • 20min
Alexander Pan on the MACHIAVELLI benchmark
Alexander Pan, a 1st-year student at Berkeley, discusses the MACHIAVELLI benchmark paper on measuring trade-offs between rewards and ethical behavior in AI agents. They explore topics like creating artificial conscience in language models, balancing rewards with morality, and addressing AI risks like negative impacts on political discourse and malware development.
