The measured horizon and the anecdotal week-long run from January 15 differ by more than an order of magnitude; the benchmark is the conservative number.
Development
The measured autonomy horizon reaches 6.6 hours
Claim
METR found GPT-5.2 at high reasoning has a record autonomy time horizon of 6.6 hours on complex software tasks, while Sam Altman said OpenAI has basically built AGI.
Reported metric: 6.6 hours
Reporting date: (not necessarily the event date)
Sources
Attribution and reporting linked by this record; links do not imply independent verification.
- Welcome to February 5, 2026 (theinnermostloop.substack.com)
Knowledge graphopen in browser →
Reported in
Cite or correct this record
Suggest a correction — opens a GitHub draft for you to review and submit.