Termsslug: task-length-doubling-time

Task-Length Doubling Time

任务时长翻倍周期

Metric for how fast the task length a model can complete autonomously grows, currently doubling about every 3.6 months.

Curated Intelligence

1 items · Page 1/1
The DecoderT2·Industry
78 pts
METR Warns AI Capability Growth Is Outpacing Safety Testing

METR's latest quarterly capability update finds frontier models now outperform experienced human professionals on most well-specified coding and computational tasks, with the task length they can handle doubling every 3.6 months; a naive extrapolation reaches 50% success on 200-hour tasks by July 2027. The organization warns that current public data cannot rule out a drastic acceleration in AI research, potentially leaving humans unable to meaningfully assess and react to catastrophic risks.