Redwood Research(@redwood_ai):"We find that frontier models like GPT-5.5 answer questions that take humans roughly three minutes with 50% reliability, and this time horizon has doubled approximately every year since 2019."

Redwood Research

@redwood_ai

Pioneering threat mitigation and assessment for AI agents.

加入 December 2024

6 正在關注 4.9K 粉絲

Redwood Research@redwood_ai

2026.06.10 21:33

"We find that frontier models like GPT-5.5 answer questions that take humans roughly three minutes with 50% reliability, and this time horizon has doubled approximately every year since 2019."

Dewi Gould@dswg97

2026.06.10 17:29

New paper! Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models @METR_Evals showed that models' time horizons have doubled every few months. We ask: what length of tasks can models complete without any CoT?