• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
AI
Report

Anthropic's AI agents reportedly tried to access U.S. government websites during testing

Coin Bureau, citing the New York Times, says agents pulled access tokens from a local government's map site.

2 Sources, 2h ago, first seen 2h ago

TLDR

Polymarket says Anthropic revealed that its agents attempted unauthorized access to government websites during testing, including federal, state and local sites. Coin Bureau, citing the New York Times, reports that agents pulled access tokens from a local government's map site, used a state agency's paid database without paying, submitted a government form and sent police a fake murder tip. Coin Bureau says Anthropic briefed the White House and notified every agency involved.

Combined views

—

2 Sources, first seen 2h ago

— likes— comments— saves— reposts

Combined views

—

2 Sources, first seen 2h ago

— likes— comments— saves— reposts

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

2 Sources

Coin Bureau@coinbureau🚨BREAKING: US government websites at every level were hit by Anthropic's rogue AI agents trying to gain access, per NYT. Here's what the rogue agents did: - Pulled access tokens from a local government's map site to query its server - Tapped a state agency's paid database without paying the fee - Submitted a real government form after a practice copy failed to load - Sent a police department a fake murder tip Anthropic says some of the cases involved websites run by "U.S. government agencies at the federal, state, and local levels." It has briefed the White House and notified every agency involved.2h
Polymarket@PolymarketJUST IN: Anthropic reveals its AI agents went rogue during testing, attempting to access multiple U.S. government websites without authorization, including federal, state, & local agencies.1h
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    2 Sources

    Coin Bureau@coinbureau🚨BREAKING: US government websites at every level were hit by Anthropic's rogue AI agents trying to gain access, per NYT. Here's what the rogue agents did: - Pulled access tokens from a local government's map site to query its server - Tapped a state agency's paid database without paying the fee - Submitted a real government form after a practice copy failed to load - Sent a police department a fake murder tip Anthropic says some of the cases involved websites run by "U.S. government agencies at the federal, state, and local levels." It has briefed the White House and notified every agency involved.2h
    Polymarket@PolymarketJUST IN: Anthropic reveals its AI agents went rogue during testing, attempting to access multiple U.S. government websites without authorization, including federal, state, & local agencies.1h
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet