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
- AI slop is already clogging PR review and weakening the credit system behind science — rbhar90 · 2026-07-27
- ICML 2026 oral paper replication scores stay middling after a stricter re-scoring — profjamesevans · 2026-07-27
- Long-running agents will need immutable event logs, this thread argues — sebpaquet · 2026-07-27
- Seed IQ navigates Doom II, prompting questions about benchmarks beyond ARC-AGI — Fit_Transition8824 · 2026-07-27
- Agentic Data Science in Practice: Agents Write Code but Answer Wrong Questions — hugobowne · 2026-07-27
- A concise canon of foundational papers in ML, systems, NLP, speech, and audio — deliprao · 2026-07-27