Research
* denotes equal contribution
Publications
A benchmark of expert-level academic questions to assess AI capabilities
Coauthor; consortium paper with >1,000 authors
Nature, 649:1139–1146, 2026
The Second World War, Inequality and the Social Contract in Britain
Leander Heldring*, James Robinson*, and Parker Whitfill*
Economica, Volume 89, Issue S1, p. S137–S159
Research Notes
The Economics of Recursive Self-Improvement
Tom Cunningham, Lukas Althoff, Basil Halperin, Brian Jabarian, Andrew Koh, Arjun Ramani, Phil Trammell, Parker Whitfill, and Cheryl Wu
Elasticity Institute, July 2026
Forecasting AI Time Horizon Under Compute Slowdowns
Parker Whitfill, Ben Snodin, and Joel Becker
Note on Selection Bias in Observational Estimates of Algorithmic Progress
Parker Whitfill
Will Compute Bottlenecks Prevent an Intelligence Explosion?
Parker Whitfill* and Cheryl Wu* (*equal contribution)
METR Blog Posts
Task Substitution and Uplift
Tom Cunningham and Parker Whitfill
May 8, 2026
Many SWE-bench-Passing PRs Would Not Be Merged into Main
Parker Whitfill, Cheryl Wu, Joel Becker, and Nate Rush
March 10, 2026
