✳flâneur — a map of the web's best reading

Andi Peng

andipeng.com · 1,250 words · saved by 2 readers

I am a Co-Founder of humans&. I was previously a researcher at Anthropic working on RL and post-training of Claude 3.5 through 4.5 and before that, a PhD student at MIT CSAIL advised by Jacob Andreas and Julie Shah. I’ve spent summers at Facebook AI Research (FAIR), Boston Dynamics AI Institute, MIT-IBM Watson AI Lab, and before grad school, two years as an AI Resident at Microsoft Research. I did my undergrad at Yale, where I got my start in research with Brian Scassellati and read a lot of dead philosophers. I’m interested in building agents that learn representations from rich human knowledge, whether directly (e.g. from users) or through priors (e.g. from LMs). Currently, I’m thinking a lot about how to utilize pretrained models in conjunction with human feedback to interactively learn aligned preferences/rewards. A history buff at heart, I care deeply about working with non-academic communities to create safe, ethical, and equitable AI. I currently serve as a Special Government Em

Andi Peng Search I am a Co-Founder of humans& . I was previously a researcher at Anthropic working on RL and post-training of Claude 3.5 through 4.5 and before that, a PhD student at MIT CSAIL advised by Jacob Andreas and Julie Shah . I've spent summers at Facebook AI Research (FAIR), Boston Dynamics AI Institute, MIT-IBM Watson AI Lab, and before grad school, two years as an AI Resident at Microsoft Research. I did my undergrad at Yale, where I got my start in research with Brian Scassellati and read a lot of dead philosophers. I'm interested in building agents that learn representations from

Explore this link on the map →

saved by

related reading