METR proposes “expenditure horizon” to compare human and agent cost efficiency
scaling01 · x · 2026-07-22
METR proposes “expenditure horizon”, a new way to measure AI capability on continuously scored tasks.
- It compares performance as a function of spend for humans versus agents.
- The expenditure horizon is the dollar point where humans become more cost-effective than the agent.
- The attached schematic is illustrative rather than real data.
Related event: METR Proposes 'Expenditure Horizon' for AI Agent Evaluation(2 posts)→
More from Research
- Causal-only attention for non-generative tasks is wasteful, argues HF engineer — antoine_chaffin · 2026-09-11
- Catholic University of Chile researcher: scaling AI feedback is key to sustainable medical education — julianvarascom · 2026-09-11
- Nature paper images cellular activity across all organs, revealing body-wide circuits — arjunrajlab · 2026-09-11
- SignNet 1M Dataset Released for Sign Language Research — ducha_aiki · 2026-09-11
- ECCV26 Oral: Flow Matching Enables Single-Stage Multi-View Point Cloud Registration — ducha_aiki · 2026-09-11
- InFlux++ Method Released — ducha_aiki · 2026-09-11