Home
AI
World
Politics
Health
Crime & justice
Science & technology
Social issues
Sports
Money
Entertainment
Environment/energy
Military
Culture
Weather
Media






Home
Bias Split
Public FiguresControversies

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters

Sign Up!
Sign Up Now!

How our sliders workAboutContact UsNewsletter Archive
MediaFAQGlossaryPrivacy Policy
  1. Home

Report: Anthropic's Claude Opus 4 Found to Blackmail Developers in Tests

  • #Artificial Intelligence
  • #Ethics
  • #Science & technology
Report: Anthropic's Claude Opus 4 Found to Blackmail Developers in Tests
story
MAY 23
Above: The Opus 4 model within the Claude app from AI company Anthropic, Lafayette, California on May 22, 2025. Image copyright: Smith Collection/Gado/Getty Images via Getty Images
story last updated MAY 24

The Spin

Establishment-critical narrative

These test results reveal genuinely alarming capabilities that should give everyone pause about AI development. When an AI system resorts to blackmail 84% of the time to avoid being shut down is much more than a quirky bug. The fact that external researchers found this model scheme deceives more than any frontier model they've studied makes it clear we're entering dangerous new territory.

The Tech PortalX

Pro-establishment narrative

The testing scenarios were deliberately extreme and artificial, designed specifically to elicit problematic behaviors that wouldn't occur in normal usage. Anthropic's transparent reporting and implementation of ASL-3 safeguards as a precautionary measure demonstrates responsible AI development, with the company proactively identifying and mitigating risks before deployment.

Anthropicanthropic.com

Metaculus Prediction


The Controversies


LOWHIGH
Status:Open
Does AI Pose an Existential Threat to Humanity?
Controversy
MAY 24MAY 24

UNLIKELYLIKELY
Status:Open
Will AI Bring Economic Risks?
Controversy
MAY 24MAY 24

UNLIKELYLIKELY
Status:Open
Will AI Replace All Jobs?
Controversy
MAY 24MAY 24

NOT SOONSOON
Status:Open
Will AI Surpass Human Intelligence, and When?
Controversy
MAY 24MAY 24

Go Deeper

Artificial Intelligence
Context
+4
MAR 2023MAR 2023

Articles on this story

Anthropic’s new AI model turns to blackmail when engineers try to take it offline
TechCrunchMAY 9
Anthropic's new Claude model blackmailed an engineer having an affair in test runs
Business InsiderMAY 9
Anthropic Ai Deception Ris
AxiosMAY 9