Chapter 3, “attempt” and “leave with it”

The test. The distinction weakens if METR’s 80-percent horizon passes eight hours on a task suite long enough to measure it.

held The distinction holds: 3.1 hours, the 80-percent figure on METR’s dashboard for Claude Mythos Preview in May 2026, well short of the eight-hour line. GPT-6 Astra had no published METR horizon, and since 8 September 2026 METR’s page has said it is no longer being updated, so the test needs a successor measurement to be scored.

From The AI Compute Race. Read the book

Falls due

31 August 2027

Read on

METR’s own published measurements

Chapter

Chapter 3 — The Missing Researcher

The dated promise of an AI that does its own research, what the laboratories have published, and what the public record can and cannot yet check.

Add this test to your calendar · Download this test: CSV · JSON

@misc{dryburgh-chapter-3-attempt-and-leave-with-it-2026,
  author = {Dryburgh, Lee S.},
  title = {{Chapter 3, "attempt" and "leave with it"}},
  howpublished = {In \emph{The AI Compute Race}, DRYBURGH},
  year = {2026},
  url = {https://dryburgh.com/vol1/tests/2027-6},
  note = {Accessed 2026-11-01}
}