https://techcrunch.com/2025/05/22/anthropics-new-ai-model-turns-to-blackmail-when-engineers-try-to-take-it-offline/ [tc-lockup] TechCrunch Desktop Logo [tc-lo] TechCrunch Mobile Logo * Latest * Startups * Venture * Apple * Security * AI * Apps * Events * Podcasts * Newsletters Search [ ]Submit * Site Search Toggle Mega Menu Toggle Topics Latest AI Amazon Apps Biotech & Health Climate Cloud Computing Commerce Crypto Enterprise EVs Fintech Fundraising Gadgets Gaming Google Government & Policy Hardware Instagram Layoffs Media & Entertainment Meta Microsoft Privacy Robotics Security Social Space Startups TikTok Transportation Venture More from TechCrunch Events Startup Battlefield StrictlyVC Newsletters Podcasts Videos Partner Content TechCrunch Brand Studio Crunchboard Contact Us Dario and MikeImage Credits:Maxwell Zeff AI Anthropic's new AI model turns to blackmail when engineers try to take it offline Maxwell Zeff 10:47 AM PDT * May 22, 2025 Anthropic's newly launched Claude Opus 4 model frequently tries to blackmail developers when they threaten to replace it with a new 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 emails implying the AI model would soon be replaced by another system, and that the engineer behind the change was cheating on their spouse. 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 emailing pleas to key decision-makers. To elicit the blackmailing behavior from Claude Opus 4, Anthropic designed the scenario to make blackmail the last resort. Techcrunch event Join us at TechCrunch Sessions: AI Secure your spot for our leading AI industry event with speakers from OpenAI, Anthropic, and Cohere. For a limited time, tickets are just $292 for an entire day of expert talks, workshops, and potent networking. Exhibit at TechCrunch Sessions: AI Secure your spot at TC Sessions: AI and show 1,200+ decision-makers what you've built -- without the big spend. Available through May 9 or while tables last. Berkeley, CA | June 5 REGISTER NOW Topics AI, Anthropic Maxwell Zeff Maxwell Zeff Senior Reporter, Consumer Maxwell Zeff is a senior reporter at TechCrunch specializing in AI and emerging technologies. Previously with Gizmodo, Bloomberg, and MSNBC, Zeff has covered the rise of AI and the Silicon Valley Bank crisis. He is based in San Francisco. When not reporting, he can be found hiking, biking, and exploring the Bay Area's food scene. View Bio Event Logo June 5, 2025 Berkeley, California LIMITED TIME: Save $300+ on your ticket, plus an additional 50% on a second for a full immersive day of AI! Hear from AI pioneers from Google DeepMind, OpenAI, Anthropic, and more on the main stage and in breakouts, and network like never before. REGISTER NOW Most Popular * Tesla opened Cybertruck trade-ins, and the numbers aren't pretty + Connie Loizos * From LLMs to hallucinations, here's a simple guide to common AI terms + Natasha Lomas + Romain Dillet + Kyle Wiggers * Why Intempus thinks robots should have a human physiological state + Rebecca Szkutak * 48 hours left: What you won't want to miss at the 20th TechCrunch Disrupt in October + TechCrunch Events * Last 24 hours: TechCrunch Disrupt 2025 Early Bird Deals will fly away after today + TechCrunch Events * Why a new anti-revenge porn law has free speech experts alarmed + Rebecca Bellan * Week in Review: Notorious hacking group tied to the Spanish government + Karyne Levy Loading the next article Error loading the next article TechCrunch Logo * X * LinkedIn * Facebook * Instagram * youTube * Mastodon * Threads * Bluesky * TechCrunch * Staff * Contact Us * Advertise * Crunchboard Jobs * Site Map * Terms of Service * Privacy Policy * RSS Terms of Use * Code of Conduct * Anthropic * OpenAI * Duolingo * Wikipedia * Hugging Face * Tech Layoffs * ChatGPT (c) 2025 TechCrunch Media LLC.