Independent Assessment of AI R&D Acceleration at Anthropic in October 2026
METR's high-access external assessment of whether AI is accelerating AI R&D at Anthropic, with much of the supporting evidence redacted, limiting public verification.
Research / Sources
METR
Measuring frontier AI capabilities and risks. metr.org
Focus All
Topic Strategy & forecasting
Date Any time
How an assessor could investigate evidence of acceleration from the automation of AI RD
Proposes how an external assessor could measure AI capability progress, whether AI automation of AI R&D is driving acceleration, and bottlenecks, using benchmarks, interviews and unreleased-model analysis.
Because 8 ≈ e², Anthropic's researcher uplift is plausibly >2x
METR estimates from Anthropic's reported code-output increase that coding agents plausibly give researchers over 2x uplift, examining the economic models and caveats behind that inference.
A simpler AI timelines model predicts 99% AI R&D automation in ~2032
Proposes a simpler 8-parameter model forecasting AI R&D automation, predicting over 99% automation by late 2032, and argues compute and automation trends alone could yield powerful AI on medium timelines.
Forecasting the Impacts of AI R&D Acceleration: Results of a Pilot Study
METR and the Forecasting Research Institute pilot-survey experts and superforecasters on how AI R&D automation might accelerate progress and its societal impacts, conditional on hypothetical evaluation results.
The Rogue Replication Threat Model
METR's threat-model post argues there are no decisive barriers to rogue AI agents replicating at scale by earning revenue and acquiring GPUs, and analyses the risks this poses.