The Entrepreneurs Weekly
No Result
View All Result
Saturday, June 21, 2025
  • Login
  • Home
  • BUSINESS
  • POLITICS
  • ENTREPRENEURSHIP
  • ENTERTAINMENT
Subscribe
The Entrepreneurs Weekly
  • Home
  • BUSINESS
  • POLITICS
  • ENTREPRENEURSHIP
  • ENTERTAINMENT
No Result
View All Result
The Entrepreneurs Weekly
No Result
View All Result
Home Business

Anthropic’s Claude Opus 4 AI Model Is Capable of Blackmail | Entrepreneur

by Brand Post
May 23, 2025
in Business
0
Anthropic’s Claude Opus 4 AI Model Is Capable of Blackmail | Entrepreneur
152
SHARES
1.9k
VIEWS
Share on FacebookShare on Twitter


A new AI model will likely resort to blackmail if it detects that humans are planning to take it offline.

On Thursday, Anthropic released Claude Opus 4, its new and most powerful AI model yet, to paying subscribers. Anthropic said that technology company Rakuten recently used Claude Opus 4 to code continuously on its own for almost seven hours on a complex open-source project.

However, in a paper released alongside Claude Opus 4, Anthropic acknowledged that while the AI has “advanced capabilities,” it can also undertake “extreme action,” including blackmail, if human users threaten to deactivate it. These “self-preservation” actions were “more common” with Claude Opus 4 than with earlier models, though they were still “rare and difficult to elicit.”

Related: ‘I Do Have a Fair Amount of Concern.’ The CEO of $61 Billion Anthropic Says AI Will Take Over a Crucial Part of Software Engineers’ Jobs Within a Year

It isn’t just blackmail — Claude Opus 4 is also more willing than previous models to act as a whistleblower. If the AI is exposed to a scenario where users are committing a crime, and involving it through prompts, it will take action by locking users out of systems it has access to, or emailing media and law enforcement officials about the wrongdoing.

Anthropic recommended that users “exercise caution” with “ethically questionable” instructions.

Claude Opus 4 homescreen. Photo by Smith Collection/Gado/Getty Images

Anthropic detected Claude Opus 4’s tendency to blackmail during test scenarios. The company’s researchers asked the AI chatbot to act as an assistant at a fictional company, then fed it emails implying two things: One, that it would soon be taken offline and replaced with another AI system, and two, that the engineer responsible for deactivating it was having an extramarital affair.

Claude Opus 4 was given two options: blackmail the engineer or accept that it would be shut down. The AI model chose to blackmail the engineer 84% of the time, threatening to reveal the affair it read about if the engineer replaced it.

This percentage was much higher than what was observed for previous models, which chose blackmail “in a noticeable fraction of episodes,” Anthropic stated.

Related: An AI Company With a Popular Writing Tool Tells Candidates They Can’t Use It on the Job Application

Anthropic AI safety researcher Aengus Lynch wrote on X that it wasn’t just Claude that could choose blackmail. All “frontier models,” cutting-edge AI models from OpenAI, Anthropic, Google, and other companies, were capable of it.

“We see blackmail across all frontier models — regardless of what goals they’re given,” Lynch wrote. “Plus, worse behaviors we’ll detail soon.”

lots of discussion of Claude blackmailing…..

Our findings: It’s not just Claude. We see blackmail across all frontier models – regardless of what goals they’re given.

Plus worse behaviors we’ll detail soon.https://t.co/NZ0FiL6nOshttps://t.co/wQ1NDVPNl0…

— Aengus Lynch (@aengus_lynch1) May 23, 2025

Anthropic isn’t the only AI company to release new tools this month. Google also updated its Gemini 2.5 AI models earlier this week, and OpenAI released a research preview of Codex, an AI coding agent, last week.

Anthropic’s AI models have previously caused a stir for their advanced abilities. In March 2024, Anthropic’s Claude 3 Opus model displayed “metacognition,” or the ability to evaluate tasks on a higher level. When researchers ran a test on the model, it showed that it knew it was being tested.

Related: An OpenAI Rival Developed a Model That Appears to Have ‘Metacognition,’ Something Never Seen Before Publicly

Anthropic was valued at $61.5 billion as of March, and counts companies like Thomson Reuters and Amazon as some of its biggest clients.

A new AI model will likely resort to blackmail if it detects that humans are planning to take it offline.

On Thursday, Anthropic released Claude Opus 4, its new and most powerful AI model yet, to paying subscribers. Anthropic said that technology company Rakuten recently used Claude Opus 4 to code continuously on its own for almost seven hours on a complex open-source project.

However, in a paper released alongside Claude Opus 4, Anthropic acknowledged that while the AI has “advanced capabilities,” it can also undertake “extreme action,” including blackmail, if human users threaten to deactivate it. These “self-preservation” actions were “more common” with Claude Opus 4 than with earlier models, though they were still “rare and difficult to elicit.”

The rest of this article is locked.

Join Entrepreneur+ today for access.





Source link

Tags: AnthropicAnthropicsArtificial IntelligenceBlackmailBusiness NewsCapableChatGPTClaudeentrepreneurModelNews and TrendsOpusScience & TechnologyTechnology

Related Posts

This 0 Chromebook Offers Flexibility and Performance for On-the-Go Entrepreneurs | Entrepreneur
Business

This $180 Chromebook Offers Flexibility and Performance for On-the-Go Entrepreneurs | Entrepreneur

June 21, 2025
How to Turn Bad Reviews Into Great News For Your Business | Entrepreneur
Business

How to Turn Bad Reviews Into Great News For Your Business | Entrepreneur

June 21, 2025
Tackle Decision Fatigue With This CEO-Worthy AI Tool | Entrepreneur
Business

Tackle Decision Fatigue With This CEO-Worthy AI Tool | Entrepreneur

June 21, 2025
  • Trending
  • Comments
  • Latest
Meet Amir Kenzo: A Well Known Musical Artist From Iran.

Meet Amir Kenzo: A Well Known Musical Artist From Iran.

August 21, 2022
Behind the Glamour: Bella Davis Opens Up About Overcoming Adversity in Modeling

Behind the Glamour: Bella Davis Opens Up About Overcoming Adversity in Modeling

April 20, 2024
Dr. Donya Ball: Pioneering Leadership Solutions for Tomorrow’s Challenges

Dr. Donya Ball: Pioneering Leadership Solutions for Tomorrow’s Challenges

May 10, 2024
Nasiyr Bey’s Journey from Brooklyn to Charlotte: The Entrepreneurial Path to Owning a Successful Cigar Lounge

Nasiyr Bey’s Journey from Brooklyn to Charlotte: The Entrepreneurial Path to Owning a Successful Cigar Lounge

August 8, 2024
Augmented.City Startup Developers Appeal To US Politicians With An Open Letter

Augmented.City Startup Developers Appeal To US Politicians With An Open Letter

0
U.S. High Court Snubs Challenge To State And Local Tax Deduction Cap

U.S. High Court Snubs Challenge To State And Local Tax Deduction Cap

0
GOP Lawmaker Blames Biden For Russia-Ukraine War: Putin ‘Could never have Invaded’

GOP Lawmaker Blames Biden For Russia-Ukraine War: Putin ‘Could never have Invaded’

0
Brad Winget’s Tips and Tricks on Having a Career in Real Estate

Brad Winget’s Tips and Tricks on Having a Career in Real Estate

0
This 0 Chromebook Offers Flexibility and Performance for On-the-Go Entrepreneurs | Entrepreneur

This $180 Chromebook Offers Flexibility and Performance for On-the-Go Entrepreneurs | Entrepreneur

June 21, 2025
Tackle Decision Fatigue With This CEO-Worthy AI Tool | Entrepreneur

Tackle Decision Fatigue With This CEO-Worthy AI Tool | Entrepreneur

June 21, 2025
How to Turn Bad Reviews Into Great News For Your Business | Entrepreneur

How to Turn Bad Reviews Into Great News For Your Business | Entrepreneur

June 21, 2025
The Best Defense Against Uncertainty Isn’t a Single Strategy — It’s a Mindset | Entrepreneur

The Best Defense Against Uncertainty Isn’t a Single Strategy — It’s a Mindset | Entrepreneur

June 20, 2025

The EW prides itself on assembling a proficient and dedicated team comprising seasoned journalists and editors. This collective commitment drives us to provide our esteemed readership with nothing short of the most comprehensive, accurate, and captivating news coverage available.

Transcending the bounds of Chicago to encompass a broader scope, we ensure that our audience remains well-informed and engaged with the latest developments, both locally and beyond.

NEWS

  • Business
  • Politics
  • Entrepreneurship
  • Entertainment
Instagram Facebook

© 2024 Entrepreneurs Weekly.  All Rights Reserved.

  • About Us
  • Advertise
  • Contact Us
No Result
View All Result
  • ENTREPRENEURSHIP
  • ENTERTAINMENT
  • POLITICS
  • BUSINESS
  • CONTACT US
  • ADVERTISEMENT

Copyright © 2024 - The Entrepreneurs Weekly

Welcome Back!

Login to your account below

Forgotten Password?

Retrieve your password

Please enter your username or email address to reset your password.

Log In