News for hackers. Stuff that matters.
Re:Measuring AI Ability to Complete Long Tasks: Opus 4.5 has... by macrolime on Sunday December 21, 2025 @10:53AM (#46345659)
I find that surprising. GPT 5.2 is the model I've had working the longest. It frequently works more than 4 hours nonstop, while earlier models would stop to ask if they should continue every 10 minutes. 5.1 and earlier ignores it if I ask it to continue until a task is done, but 5.2 will usually finish it.

There are no comments on this comment yet.