Toby Ord finds most measured reasoning gains came from longer inference

DoomBench assesses “Toby Ord finds most measured reasoning gains came from longer inference” as evidence moving away from doom, with magnitude 30 and confidence 72 out of 100 in the human resilience category.

The DoomBench assessment of “Toby Ord finds most measured reasoning gains came from longer inference” is based on reporting from Toby Ord and records the editorial rationale, source quality, attribution, and revision history.

DoomBench summarizes “Toby Ord finds most measured reasoning gains came from longer inference” as follows: Toby Ord estimated that 63% to 92% of measured reasoning gains on three benchmarks came from using more inference tokens rather...