Jan Leike(@janleike)

New research result: we use Claude to make fully autonomous progress on scalable oversight research,...

8.0内容质量
New research result: we use Claude to make fully autonomous progress on scalable oversight research,...

TL;DR · AI 摘要

新研究表明Claude在可扩展监督研究中显著优于人类研究员,成本为18k积分。

核心要点

  • Claude实现自主研究突破
  • 性能差距恢复指标提升
  • 相比人类研究员更具成本效益
#Claude#AI研究#自动化#可扩展性
打开原文

Claude iterates on a number of different techniques and ends up significantly outperforming human researchers for $18k in credits. https://t.co/fbVpCPPtaU" / X

Jan Leike on X: "New research result: we use Claude to make fully autonomous progress on scalable oversight research, as measured by performance gap recovered (PGR). Claude iterates on a number of different techniques and ends up significantly outperforming human researchers for $18k in credits. https://t.co/fbVpCPPtaU" / X

Don’t miss what’s happening

Image 2
Image 2

Jan Leike

@janleike

New research result: we use Claude to make fully autonomous progress on scalable oversight research, as measured by performance gap recovered (PGR). Claude iterates on a number of different techniques and ends up significantly outperforming human researchers for $18k in credits.

Image 3: Image
Image 3: Image

7:43 PM · Apr 14, 2026

·

137.4K Views

33

141

1.2K

604

Read 33 replies