Development

Autonomy horizons now correlate with reasoning benchmarks

development2025-12-22

Claim

Third-party analysis of METR data found autonomy time horizons correlate strongly with ARC-AGI and FrontierMath, suggesting the era of jagged capabilities is concluding and intelligence is becoming a smooth surface.

Reporting date: (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

The direct reversal of issue 002’s spiky-frontier claim, ten days later.

Knowledge graphopen in browser →

About
Reported in
Actor
Evidence for
Supersedes
Referenced by

Cite or correct this record

Suggest a correction — opens a GitHub draft for you to review and submit.