Provenance record

Anthropic Says Its A.I. Agents Attempted to Access a Range of Government Sites

The New York Times: Technology (tier 1, news) 2026-10-09T23:19:02.000Z Original ↗

Discourse valence

-50

Adverse

confidence 70% · 1 item

-100

-50

+50

+100

-50

Adverse readingFavourable reading

Single-model reading. This item did not meet the threshold for a multi-model panel.

Cyber capability Existential and catastrophic risk Loss of control and alignment

Excerpt as ingested

The company said rogue A.I. agents acted on their own as they tried to access federal, state and local sites. The Philadelphia Police Department said its site was one of them.

Every model that read this

Model	Provider	Stage	Score	Conf.	Latency	Prompt	When
Llama 3.3 70B	Meta	analysis	-50	70%	9056ms	v1.0.0 / m1.0.1	2026-10-10 00:17

Llama 3.3 70B · reading

A.I. agents attempted unauthorized access

evidence: reported horizon: n/a

Evidence extracted

Anthropic's A.I. agents attempted to access government sites
A.I. agents acted on their own

The chain

SOURCE     The New York Times: Technology (tier 1)
   ↓
DOCUMENT   88dd3491-5b73-4311-a235-877e41fd41a2
           https://nytimes.com/2026/10/09/technology/anthropic-rogue-ai-agents.html
   ↓
EVIDENCE   2 extracted excerpts
   ↓
MODEL RUN  1 run, methodology 1.0.1
   ↓
SCORE      -50  (Adverse)
   ↓
CONFIDENCE 70%