Palisade researcher: judge AI by real work, not 40 benchmarks

Palisade Research's Jeff Ladish argues that AI progress should be measured by whether agents can autonomously complete economically valuable real work, not by piling up 40 benchmarks, and calls for reviving METR's time-horizon charts.

2026-11-06 ~ 2026-11-06 · 2 related posts

• Palisade's Jeff Ladish calls to revive METR time-horizon estimates for new models — JeffLadish · 2026-11-06
• Palisade's Jeff Ladish: skip the 40 benchmarks, ask if agents finish real work — FinanceYF5 · 2026-11-06