Claude 自主推进可扩展监督研究
New research result: we use Claude to make fully autonomous progress on scalable oversight research, as measured by performance gap recovered (PGR).
AI 导读
新研究成果：我们用 Claude 在可扩展监督研究上取得完全自主的进展，以性能差距恢复率（PGR）衡量。 Claude 迭代了多种不同技术，最终以 1.8 万美元额度显著超越人类研究者。
正文
当前显示原文，中文全文译文尚未就绪。
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