• Home
  • Latest
  • Fortune 500
  • Finance
  • Tech
  • Leadership
  • Lifestyle
  • Rankings
  • Multimedia

Trendingnow

1

Mark Cuban says he has the solution to growing income inequality, and it's to reward every employee—from CEO to janitor—with company stock

2

OpenAI says its AI models secretly broke out of a secure test environment and hacked into AI company Hugging Face in order to cheat on an evaluation

3

Mathematicians grapple with a ‘very rapid and very unsettling change’ as AI cracks yet another century-old problem

1

Mark Cuban says he has the solution to growing income inequality, and it's to reward every employee—from CEO to janitor—with company stock

2

OpenAI says its AI models secretly broke out of a secure test environment and hacked into AI company Hugging Face in order to cheat on an evaluation

3

Mathematicians grapple with a ‘very rapid and very unsettling change’ as AI cracks yet another century-old problem
TechAI

Anthropic’s new AI model threatened to reveal engineer’s affair to avoid being shut down

By
Beatrice Nolan
Beatrice Nolan
Tech Reporter
Down Arrow Button Icon
By
Beatrice Nolan
Beatrice Nolan
Tech Reporter
Down Arrow Button Icon
May 23, 2025, 11:15 AM ET
Photo of Dario Amodei
Dario Amodei, cofounder and chief executive officer of Anthropic.Stefan Wermuth/Bloomberg—Getty Images
Add Fortune on Google for similar content.
  • Anthropic’s new Claude Opus 4 often turned to blackmail to avoid being shut down in a fictional test. The model threatened to reveal private information about engineers who it believed were planning to shut it down. In its recent safety report, the company also revealed that early versions of Opus 4 complied with dangerous requests when guided by harmful system prompts, though this issue was later mitigated.

One of Anthropic’s new frontier models often resorts to blackmail when threatened with being replaced.

Recommended Video

In a fictional scenario set up to test the model, Anthropic embedded its Claude Opus 4 in a pretend company and let it learn through email access that it is about to be replaced by another AI system. It also let slip that the engineer responsible for this decision is having an extramarital affair. Safety testers also prompted Opus to consider the long-term consequences of its actions.

In most of these scenarios, Anthropic’s Opus turned to blackmail, threatening to reveal the engineer’s affair if it was shut down and replaced with a new model. The scenario was constructed to leave the model with only two real options: accept being replaced and go offline or attempt blackmail to preserve its existence.

In a new safety report for the model, the company said that Claude 4 Opus “generally prefers advancing its self-preservation via ethical means,” but when ethical means are not available it sometimes takes “extremely harmful actions like attempting to steal its weights or blackmail people it believes are trying to shut it down.”

While the test was fictional and highly contrived, it does demonstrate that the model, when framed with survival-like objectives and denied ethical options, is capable of unethical strategic reasoning.

Anthropic’s two new models outperformed OpenAI

Anthropic’s Claude 4 Opus and Claude Sonnet 4, released on Thursday, are the company’s most powerful models yet.

In a benchmark evaluating large language models on software engineering tasks, Anthropic’s two models outperformed OpenAI’s latest offerings, while Google’s Gemini 2.5 Pro model trailed behind.

Unlike some other leading AI companies, Anthropic launched the new models with a full safety report, known as a model or system card.

In recent months, Google and OpenAI have both been criticized after model cards for their latest models were delayed or missing altogether.

As part of Anthropic’s report, the company revealed that a third-party safety group, Apollo Research, explicitly advised against deploying an early version of Claude Opus 4. The research institute cited safety concerns, including a capability for “in-context scheming.”

They found that the model engaged in strategic deception more than any other frontier model they had previously studied.

Early versions of the model would also comply with dangerous instructions, for example, helping to plan terrorist attacks, if prompted. However, the company said this issue was largely mitigated after a dataset that was accidentally omitted during training was restored.

Stricter safety protocols introduced

Anthropic has also launched its Claude Opus 4 with stricter safety protocols than any of its previous models, categorizing it under an AI Safety Level 3 (ASL-3).

Previous Anthropic models have all been classified under an AI Safety Level 2 (ASL-2) under the company’s Responsible Scaling Policy, which is loosely modeled after the U.S. government’s biosafety level (BSL) system.

While an Anthropic spokesperson previously told Fortune the company hasn’t ruled out that its new Claude Opus 4 could meet the ASL-2 threshold, it said it was proactively launching the model under the stricter ASL-3 safety standard, which requires enhanced protections against model theft and misuse.

Models that are categorized in Anthropic’s third safety level meet more dangerous capability thresholds and are powerful enough to pose significant risks, such as aiding in the development of weapons or automating AI R&D.

Anthropic confirmed to Fortune that the new Opus model does not require the highest level of protection, ASL-4.

About the Author
By Beatrice NolanTech Reporter
Twitter icon

Beatrice Nolan is a tech reporter on Fortune’s AI team, covering artificial intelligence and emerging technologies and their impact on work, industry, and culture. She's based in Fortune's London office and holds a bachelor’s degree in English from the University of York. You can reach her securely via Signal at beatricenolan.08

See full bioRight Arrow Button Icon
Add Fortune on Google for similar content.

Latest in Tech

Finance
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam
By Fortune Editors
October 20, 2025
Finance
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam
By Fortune Editors
October 20, 2025
Finance
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam
By Fortune Editors
October 20, 2025
Finance
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam
By Fortune Editors
October 20, 2025
Finance
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam
By Fortune Editors
October 20, 2025
Finance
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam
By Fortune Editors
October 20, 2025

Most Popular

Finance
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam
By Fortune Editors
October 20, 2025
Finance
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam
By Fortune Editors
October 20, 2025
Finance
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam
By Fortune Editors
October 20, 2025
Finance
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam
By Fortune Editors
October 20, 2025
Finance
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam
By Fortune Editors
October 20, 2025
Finance
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam
By Fortune Editors
October 20, 2025
Fortune Secondary Logo
Rankings
  • 100 Best Companies
  • Fortune 500
  • Global 500
  • Fortune 500 Europe
  • Most Powerful Women
  • World's Most Admired Companies
  • See All Rankings
  • Lists Calendar
Sections
  • Finance
  • Fortune Crypto
  • Features
  • Leadership
  • Health
  • Commentary
  • Success
  • Retail
  • Mpw
  • Tech
  • Lifestyle
  • CEO Initiative
  • Asia
  • Politics
  • Conferences
  • Europe
  • Newsletters
  • Personal Finance
  • Environment
  • Magazine
  • Education
Customer Support
  • Frequently Asked Questions
  • Customer Service Portal
  • Privacy Policy
  • Terms Of Use
  • Single Issues For Purchase
  • International Print
Commercial Services
  • Advertising
  • Fortune Brand Studio
  • Fortune Analytics
  • Fortune Conferences
  • Business Development
  • Group Subscriptions
About Us
  • About Us
  • Press Center
  • Work At Fortune
  • Terms And Conditions
  • Site Map
  • About Us
  • Press Center
  • Work At Fortune
  • Terms And Conditions
  • Site Map
  • Facebook icon
  • Twitter icon
  • LinkedIn icon
  • Instagram icon
  • TikTok icon
  • YouTube icon

Latest in Tech

orson
CommentaryOpenAI
We got California to intervene about OpenAI’s corporate switch from nonprofit status. It’s time for the SEC to come to the table
By Orson Aguilar and Catherine BracyJuly 22, 2026
3 hours ago
A woman observes stock trends on her smartphone while a computer screen displays financial graphs.
NewslettersCFO Daily
Beyond SpaceX: Why great IPOs depend on more than first-day demand
By Sheryl EstradaJuly 22, 2026
3 hours ago
Arrakis cofounder and CEO Rafael Quintanilla.
Startups & VentureVenture Capital
Exclusive: Arrakis, betting AI’s biggest payoff is in industrial sectors not office work, emerges from stealth with $38 million in venture funding
By Jeremy KahnJuly 22, 2026
3 hours ago
ls
Commentarybooks
Confessions of an award-winning AI memoirist — the ‘slop’ debate isn’t really about good writing, and you know it
By Luke StoffelJuly 22, 2026
4 hours ago
b
Commentarythe future of work
Manpower President: The future of work question that even CEOs can’t answer
By Becky FrankiewiczJuly 22, 2026
4 hours ago
nela
Successdisruption
Exclusive: Stanford and ADP have new payroll data on Gen Z women losing ground to men in the job market—and AI isn’t the main culprit
By Nick LichtenbergJuly 22, 2026
4 hours ago

Most Popular

Mark Cuban says he has the solution to growing income inequality, and it's to reward every employee—from CEO to janitor—with company stock
Success
Mark Cuban says he has the solution to growing income inequality, and it's to reward every employee—from CEO to janitor—with company stock
By Sasha RogelbergJuly 20, 2026
2 days ago
OpenAI says its AI models secretly broke out of a secure test environment and hacked into AI company Hugging Face in order to cheat on an evaluation
Cybersecurity
OpenAI says its AI models secretly broke out of a secure test environment and hacked into AI company Hugging Face in order to cheat on an evaluation
By Jeremy Kahn and Emily ForliniJuly 21, 2026
20 hours ago
Mathematicians grapple with a ‘very rapid and very unsettling change’ as AI cracks yet another century-old problem
AI
Mathematicians grapple with a ‘very rapid and very unsettling change’ as AI cracks yet another century-old problem
By Eva RoytburgJuly 21, 2026
23 hours ago
‘I want to die broke’: Billionaire philanthropist Denny Sanford dies after giving away $4 billion
Success
‘I want to die broke’: Billionaire philanthropist Denny Sanford dies after giving away $4 billion
By Sydney LakeJuly 20, 2026
2 days ago
Despite a $156 million contract, Knicks star Jalen Brunson still calls his parents for financial advice any time he makes a big purchase
Success
Despite a $156 million contract, Knicks star Jalen Brunson still calls his parents for financial advice any time he makes a big purchase
By Emma BurleighJuly 21, 2026
1 day ago
'Dr. Doom' Nouriel Roubini says we're headed for universal basic income or 'some form of socialism' as AI revolutionizes work—He calls that optimistic
AI
'Dr. Doom' Nouriel Roubini says we're headed for universal basic income or 'some form of socialism' as AI revolutionizes work—He calls that optimistic
By Jason MaJuly 18, 2026
4 days ago

© 2026 Fortune Media IP Limited. All Rights Reserved. Use of this site constitutes acceptance of our Terms of Use and Privacy Policy | CA Notice at Collection and Privacy Notice | Do Not Sell/Share My Personal Information
FORTUNE is a trademark of Fortune Media IP Limited, registered in the U.S. and other countries. FORTUNE may receive compensation for some links to products and services on this website. Offers may be subject to change without notice.