We evaluate DeepCode on the PaperBench benchmark (released by OpenAI), a rigorous testbed requiring AI agents to independently reproduce 20 ICML 2024 papers from scratch. The benchmark comprises 8,316 ...

Do you have a topic you would like to present or see presented in a future episode? Use the form and let us know.

Choose from over 350 graduate and professional programs that offer opportunities to learn across disciplines, in the classroom, online, hands-on here, or anywhere around the world. Explore our list of ...