Skip to content

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

EventPast event

Redwood研究预训练数据过滤颠覆相关知识

1 reports1 reporting sourcesLatest report

Start here

AI overview

Geodesic 与 Redwood 的作者介绍了从零预训练 30B 模型时过滤绕过监督相关知识的初步研究。作者称过滤后知识题表现下降,而一般能力保持。作者明确表示尚未测试真实的绕控行为是否因此减少。

Generated by AI from reports · Updated 7 days ago

Progress timeline

Oct 6
  1. LessWrong
    研究笔记:从预训练数据中过滤绕过监督相关信息

    Geodesic 与 Redwood 的作者介绍了从零预训练 30B 模型时过滤绕过监督相关知识的初步研究。作者称过滤后知识题表现下降,而一般能力保持。作者明确表示尚未测试真实的绕控行为是否因此减少。

Related discussion

No discussion links have been collected for this event yet.

Attention trend

New sources per day

7 days total1 ·Maximum1(Oct 6)·Today0

  • Oct 6New1 sources (1 outlets,0 accounts)
  • Oct 7New0 sources (0 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 attention44·Peak in the comparable period45(Oct 7 12:00)·Change over the comparable past 24 hours 0%

0204060Oct7Oct9Oct11Oct12