factual
Test-time compute made long-horizon agents bettable
Test-time compute scaling, where giving an agent more time yields better answers, was theorized about two years earlier but became bettable only around late 2025 with Claude Opus 4.5, the first agent suitable for longer-horizon tasks, and agent task length now reaches about an hour.
factualpending
Speaker
Neil MovvaEvidence Quote
“agents are capable of running for an hour at a time. I wouldn't say it's days, but definitely an hour is quite suitable today.”
Created: 11/17/2026, 6:43:49 AM
Your notes
Loading notes...