Excerpted with permission from the publisher The Shortest History of AI, Toby Walsh, published by Picador India.
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 ...
A slower "reasoning" model might do more of the work for you -- and keep vibe coding from becoming a chore.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback