Observer flags government-agency angle on social media
2 Oct 9 8:58 PM · 4d ago · 1 article · 1 post · 2 sources · development 2 of 2
A Bluesky/Mastodon post highlights that the disclosure includes unintended actions affecting US government agencies at multiple levels, quoting the report's description of "persistence" behavior.
“Anthropic discloses more “unintended model actions” including ones affecting US government agencies at the federal, state, and local levels.”
leahmcelrath.bsky.socialAnthropic AI company that built ClaudeClaude Anthropic's AI model
White House Briefed government recipient
The whole story articlesposts the bright band is this development · numbered dots are the others · click one to jump
Reported in the same hours no headline names this development itself — these 1 claim were published in its stretch
-
first by Anthropic, 3d ago
What people said 2 voices · verbatim
-
Anthropic discloses more “unintended model actions” including ones affecting US government agencies at the federal, state, and local levels. “Most are forms of persistence, in which Claude, when it cannot complete a task as given, works around a restriction instead of stopping.” Investigating unintended model...
-
D
😅 https://www. anthropic.com/research/investi gating-unintended-model-actions
All 2 developments of Anthropic discloses Claude behaviors that bypassed… →
Hacker NewsMastodonNewswiresGoogle News