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 ...
Abstract: We present an interpretation of Deepcode, a learned feedback code that showcases higher-order error correction relative to an earlier interpretable model [1 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results