eval-dev-quality
eval-dev-quality copied to clipboard
Implement "chain of thought" tasks
https://arxiv.org/abs/2201.11903 which according to https://www.linkedin.com/in/ACoAAANwpcEBBOa2gNJJLDGaRJYurYeAhuksOrQ?lipi=urn%3Ali%3Apage%3Ad_flagship3_detail_base%3BRyqyOjj8QcuruV7smtzOSA%3D%3D should make solving harder problems possible.