Snorkel AI tests whether agents can build libraries other agents can use

Led by Gabriel Orlanski, LibraryDesignBench scores generated libraries by the correctness and simplicity of downstream code across 242 programming problems.

By · Published

Snorkel AI tests whether agents can build libraries other agents can use — Led by Gabriel Orlanski, LibraryDesignBench scores generated libraries by the correctness and simplicity of downstream code across 242 programming problems.

Led by Gabriel Orlanski, LibraryDesignBench scores generated libraries by the correctness and simplicity of downstream code across 242 programming problems.