Search Results for author:
Found 2 papers, 2 papers with code
RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts
We confirm that our experts make progress in the environments given 8 hours, with 82% of expert attempts achieving a non-zero score and 24% matching or exceeding our strong reference solutions.
Localizing Model Behavior with Path Patching
Localizing behaviors of neural networks to a subset of the network's components or a subset of interactions between components is a natural first step towards analyzing network mechanisms and possible failure modes.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
