Measuring AI Ability to Complete Long Tasks: Opus 4.5 has 50% horizon of 4h49M
https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/
#HackerNews #MeasuringAI #LongTasks #Opus4.5 #AIResearch #TaskCompletion
Measuring AI Ability to Complete Long Tasks: Opus 4.5 has 50% horizon of 4h49M
https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/
#HackerNews #MeasuringAI #LongTasks #Opus4.5 #AIResearch #TaskCompletion