Agent Autonomy
How far AI agents can plan, persist, and execute meaningful work on their own.
This category contains 6 tracked predictions. Each page includes the original claim, current evidence, counterevidence, and what would change our assessment.
Agent-1 is bad at even simple long-horizon tasks (page 7, Early 2026 section). Also: agents in Mid 2025 are 'impressive in theory but in practice unreliable.'
The safety team finds that if Agent-2 somehow escaped and wanted to 'survive' and 'replicate' autonomously, it might be able to do so.
The better agents are also expensive; you get what you pay for, and the best performance costs hundreds of dollars a month.
Advertisements for computer-using agents emphasize the term 'personal assistant': you can prompt them with tasks like 'order me a burrito on DoorDash' or 'open my budget spreadsheet and sum this month's expenses.'
METR time horizons doubled every 7 months from 2019-2024 and every 4 months from 2024-onward (Appendix G, page 51). The acceleration from 7-month to 4-month doubling is a key claim.
AI agents become increasingly useful for real tasks but remain unreliable on complex, multi-step workflows.