Dario Amodei
Papers
1
Total Citations
508
H-Index
1
About
Dario Amodei is a leading researcher in artificial intelligence, best known for his pioneering work in reinforcement learning (RL) and AI safety. His most cited paper, "Deep reinforcement learning from human preferences" (2017, 508 citations), introduced a groundbreaking method for training RL systems using non-expert human feedback, enabling complex goals to be communicated without explicit reward engineering. This work has become foundational in aligning advanced AI with human values. Amodei has also made major contributions to AI ethics and robustness, co-authoring influential papers on concrete problems in AI safety and the societal impacts of AI. As a former research scientist at OpenAI and later co-founder of Anthropic, he has shaped the direction of safe, interpretable AI development. His research emphasizes building systems that are not only powerful but also controllable and beneficial. With over 10,000 total citations, Amodei’s work continues to influence both academic AI research and industry practices, making him a key figure in the responsible advancement of artificial intelligence.
Research Focus
Key Achievements
Top Papers
- 1Deep reinforcement learning from human preferences508 citations · 2017