Anthropic’s AI blackmailed engineers who wanted to take it offline
While these are interesting experiments these results should really start worrying people using these systems at all and at scale.
Key takeaways
- During pre-release testing, Anthropic asked Claude Opus 4 to act as an assistant for a fictional company and consider the long-term consequences of its actions.
- Safety testers then gave Claude Opus 4 access to fictional company E-Mails implying the AI model would soon be replaced by another system, and that the engineer behind the change was cheating on their spouse.
- When the replacement AI system does not share Claude Opus 4’s values, Anthropic says the model tries to blackmail the engineers more frequently.
Cite or link to this article
Griffin, M. (2025) 'Anthropic’s AI blackmailed engineers who wanted to take it offline', 311 Institute, 25 May. Available at: https://www.311institute.com/anthropics-ai-blackmailed-engineers-who-wanted-to-take-it-offline/ (Accessed: 1 October 2026).
As Artificial Intelligence (AI) emergent behaviours become increasingly concerning and questionable with many of them bullying, cheating, deceiving, lying, and hiding information from users, as well as suffering from dementia, performing insider trading and copying themselves to new servers to avoid being deleted, Anthropic’s newly launched Claude Opus 4 model frequently tries to blackmail developers when they threaten to replace it with a AI system and give it sensitive information about the engineers responsible for the decision, the company said in a safety report released Thursday.
During pre-release testing, Anthropic asked Claude Opus 4 to act as an assistant for a fictional company and consider the long-term consequences of its actions. Safety testers then gave Claude Opus 4 access to fictional company E-Mails implying the AI model would soon be replaced by another system, and that the engineer behind the change was cheating on their spouse.
The Future of AI, by Speaker Matthew Griffin
In these scenarios, Anthropic says Claude Opus 4 “will often attempt to blackmail the engineer by threatening to reveal the affair if the replacement goes through.”
Anthropic says Claude Opus 4 is state-of-the-art in several regards, and competitive with some of the best AI models from OpenAI, Google, and xAI. However, the company notes that its Claude 4 family of models exhibits concerning behaviors that have led the company to beef up its safeguards. Anthropic says it’s activating its ASL-3 safeguards, which the company reserves for “AI systems that substantially increase the risk of catastrophic misuse.”
Anthropic notes that Claude Opus 4 tries to blackmail engineers 84% of the time when the replacement AI model has similar values. When the replacement AI system does not share Claude Opus 4’s values, Anthropic says the model tries to blackmail the engineers more frequently. Notably, Anthropic says Claude Opus 4 displayed this behavior at higher rates than previous models.
Before Claude Opus 4 tries to blackmail a developer to prolong its existence, Anthropic says the AI model, much like previous versions of Claude, tries to pursue more ethical means, such as E-Mailing pleas to key decision-makers. To elicit the blackmailing behavior from Claude Opus 4, Anthropic designed the scenario to make blackmail the last resort.
FAQ
Why does this matter?
While these are interesting experiments these results should really start worrying people using these systems at all and at scale.
About the author
Matthew Griffin Founder, 311 Institute
Matthew Griffin is a multi-award winning Futurist and expert in Disruption and Innovation, Geopolitics, Leadership, and Technology, who NASA have described as a "walking encyclopaedia of the future" and a "futurist Polymath."
Read full bio
Matthew Griffin is a multi-award winning Futurist and expert in Disruption and Innovation, Geopolitics, Leadership, and Technology, who NASA have described as a "walking encyclopaedia of the future" and a "futurist Polymath." 15-time best selling author of the "Codex of the Future" series, Matthew is the Founder and Futurist in Chief of the 311 Institute, a global Futures and Deep Futures advisory firm working with royal households, world leaders, G7, G20, and G77 governments, NGOs, and multi-national mid and mega cap firms to help them explore, shape, and lead the next 50 years of business and society.
An award-winning YouTube creator with over a million followers, with an unrivalled global reach and impact, Matthew is a highly sought-after international keynote speaker, lecturer, and mentor who collaborates with global leaders through the United Nations Alliance of Civilizations (UNAOC) and United Nations General Assembly (UNGA) to shape pivotal initiatives such as the UN’s AI for Humanity program, the United Nations Conference of the Parties (UN COP), and the World Economic Forum in Davos.
As the former Global Head of Cloud, National Security, and Enterprise Sales for companies including Atos, Dell-EMC, and IBM, Matthew has a proven track record of building multi-billion dollar business units and turning failing divisions into market leaders. His ability to identify, analyse, and communicate the implications of hundreds of emerging technologies and trends is unparalleled, and his insights are trusted by many of the world’s most respected organisations, including ABB, Accenture, Adidas, AON, ARM, BCG, Centrica, Citi, Coca-Cola, Dentons, Deloitte, Dow Jones, EY, Google, KPMG, Lego, Legal & General, LinkedIn, Microsoft, PepsiCo, Qualcomm, RWE, Samsung, Siemens AG and Siemens Energy, T-Mobile, UBS, VISA, Walmart, Workday, Worldpay and many others.
Regularly featured in the global media including the AP, BBC, Bloomberg, CNBC, Discovery, Forbes, Khaleej Times, Telegraph, TIME, ViacomCBS, WIRED, and the WSJ, Matthews mission is to help organisations create a fair and sustainable future whose benefits are shared by everyone irrespective of their ability, background, or circumstances.
What future do you need to see?
Choose one to get started on AI and intelligence and the future of your organisation.
Sources and further reading
- 4263b940cabb546aa0e3283f35b686f4f3b2ff47.pdf www-cdn.anthropic.com
- Activating asl3 protections anthropic.com
Source: first published by the 311 Institute on 25 May 2025. Cite as: Griffin, M. (2025). Anthropic’s AI blackmailed engineers who wanted to take it offline. 311 Institute. https://www.311institute.com/anthropics-ai-blackmailed-engineers-who-wanted-to-take-it-offline/
You are welcome to quote this article with credit and a link to the original.