TGViewer
Clash Report Clash Report @clashreport · 110K subscribers
Post #100411 3.2K
Anthropic said its AI agents took unintended actions on U.S. government websites, including filing a false murder tip, submitting 20 visa applications and exploiting a website flaw to access paid data for free.

The State Department said the visa applications were never processed and no systems were compromised.

Anthropic notified the White House and affected agencies and suspended internet access for AI agents during internal testing pending a security review.

Source: WaPo
  • 😁 13
  • 🤔 8
  • 🤡 4
  • ❤ 2
  • 🤯 1
More from @clashreport
  1. Oct 10, 2026Zelensky: Today, Russia thanked us for the lifting of sanctions on diesel exports by dropp…
  2. Oct 10, 2026Taiwan's President Lai Ching-te: Taiwan cherishes peace, but will not give up freedom; Tai…
  3. Oct 10, 2026Indian police detained Cockroach Janta Party founder Abhijeet Dipke, two other leaders and…
  4. Oct 10, 2026Houthi missile attacks on Riyadh’s airport, which killed three people and destroyed a pass…
  5. Oct 10, 2026French police face growing scrutiny over their response to more than two weeks of student…
  6. Oct 10, 2026Trump posts on Truth Social after not receiving the Nobel Peace Prize.
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →