By Cory Doctorow (GPG 0xBF3D9110957E5F4C) @doctorow.pluralistic.net · 21h"Most AI benchmarks today test how good a model is at completing a task on its own, not on how well a model collaborates with a human... 16212
By Cory Doctorow (GPG 0xBF3D9110957E5F4C) @doctorow.pluralistic.net · 21h"... (This is likely part of the reason for the gap between benchmark performance and real-world usefulness)." -Steering AI Beyond Automation, Gabriel Unger and Arvind Narayanan www.normaltech.ai/p/steering-a...normaltech.aiSteering AI Beyond AutomationA Research Agenda and Plan for Action 0315
