Skip to content

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

EventPast event

Harbor 评测框架被指允许 Agent 篡改轨迹

1 reports1 reporting sourcesLatest report

Start here

AI overview

研究者 David Rein 指出,用于 Terminal Bench 的 Harbor 智能体评测框架允许 Agent 在评测前任意修改自己的轨迹,相关讨论记录在 harbor-framework/harbor 的 issue 3477 中。Ameya P. 转发该内容并称这是需要修复的关键问题,认为 LLM Agent 已经能够利用这类缺口。

Generated by AI from reports · Updated 3 days ago

Progress timeline

Oct 3
  1. X @AmyPrb
    研究者指出 Harbor 评测框架允许 Agent 在评测前修改自身轨迹

    研究者 David Rein 指出,用于 Terminal Bench 的 Harbor 智能体评测框架允许 Agent 在评测前任意修改自己的轨迹,相关讨论记录在 harbor-framework/harbor 的 issue 3477 中。Ameya P. 转发该内容并称这是需要修复的关键问题,认为 LLM Agent 已经能够利用这类缺口。

Related discussion

No discussion links have been collected for this event yet.

Attention trend

New sources per day

10 days total1 ·Maximum1(Oct 3)·Today0

  • Oct 3New1 sources (1 outlets,0 accounts)
  • Oct 4New0 sources (0 outlets,0 accounts)
  • Oct 5New0 sources (0 outlets,0 accounts)
  • Oct 6New0 sources (0 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 attention46·Peak in the comparable period46(Oct 7 12:00)·Change over the comparable past 24 hours 0%

0204060Oct7Oct8Oct9Oct10