Skip to content

Translation in progress Some entries still include text in the original language.

EventPast event

Anthropic在Claude 3.7发布前处理危险能力评估

1 reports1 reporting sourcesLatest report

Start here

AI overview

Vanity Fair报道称，Anthropic前沿红队在Claude 3.7 Sonnet发布前三天收到一批评估结果，其“能力提升差值”远超预期：在开发生物武器等恶意任务的测试中，可使用Claude的受试者成功率明显高于仅用Google和教科书的对照组。按Anthropic 2023年发布的Responsible Scaling Policy，该结果在部分极端场景下触及ASL-3阈值，团队需在三天内决定是否推迟发布。

Generated by AI from reports · Updated 5 days ago

Latest update
Anthropic 前沿红队发现 Claude 3.7 Sonnet 危险能力评估结果异常

Progress timeline

Oct 7
  1. Vanity Fair
    Anthropic 前沿红队发现 Claude 3.7 Sonnet 危险能力评估结果异常

    Anthropic 前沿红队在 Claude 3.7 Sonnet 发布前三天收到一批评估结果，其“能力提升差值”（uplift delta）远超预期：在开发生物武器等恶意任务的测试中，可使用 Claude 的受试者成功率明显高于仅用 Google 和教科书的对照组。按 Anthropic 2023 年发布的 Responsible Scaling Policy，该结果在部分极端场景下触及 ASL-3 阈值，团队需在三天内决定是否推迟发布。

Related discussion

No discussion links have been collected for this event yet.

Attention trend

New sources per day

6 days total1 ·Maximum1（Oct 7）·Today0

  • Oct 7New1 sources (1 outlets,0 accounts)
  • Oct 8New0 sources (0 outlets,0 accounts)
  • Oct 9New0 sources (0 outlets,0 accounts)
  • Oct 10New0 sources (0 outlets,0 accounts)
  • Oct 11New0 sources (0 outlets,0 accounts)
  • Oct 12New0 sources (0 outlets,0 accounts)

Hourly attention

Current attention34·Peak in the comparable period37（Oct 8 06:00）·Change over the comparable past 24 hours 0%

010203040Oct8Oct9Oct11Oct12