Collin Burns AI researcher focused on AI alignment, evaluation, and understanding the internal behavior of language models. His work includes weak-to-strong generalization, latent-knowledge elicitation, and benchmark development. He previously worked at OpenAI and Anthropic.
Collin Burns AI researcher focused on AI alignment, evaluation, and understanding the internal behavior of language models. His work includes weak-to-strong generalization, latent-knowledge elicitation, and benchmark development. He previously worked at OpenAI and Anthropic.
Career
Collin Burns studied at University of California, Berkeley (Doctoral study in Computer Science).