Anthropic's Claude Opus 4 AI Model Is Capable of Blackmail

When given the choice between blackmail and being deactivated, Claude Opus 4 chose blackmail 84% of the time.
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.

Try Our AI Features

Explore what Daily8 AI can do for you:

Learn with AIFact CheckingText to SpeechAI Summary

Related Articles

Business Insider

15 minutes ago

• Business Insider

I made an AI tool to run my job search, and it helped me get my dream role

Mark Quinn is the senior director of AI operations for Pearl, an AI search platform for professional services. Before getting the job, the longtime tech exec, who'd held leadership roles at Waymo, Apple, and LinkedIn, created an artificial intelligence tool, now called CareerBuddy GPT, to help level up his search. The tool determined whether he was a good fit, updated his résumé to highlight relevant experience, wrote cover letters, and identified people to contact about the position. The following has been edited for brevity and clarity. When I turned to AI to help with my job search, I was five months into it and wasn't getting the traction that I thought I would get. I felt like I had done everything, which obviously was not the case. When you're in a moment like this, you can feel stuck and be blinded to the possibilities. So, I went to AI and said, "I don't know what to do. I'm an exec in tech, and here's my résumé. I'm applying to these jobs, and I'm not having a lot of success." It was able to walk me back from the edge and say, essentially, "Look, you're at this level, and your average job search time should be ABC, and you're only this far in. So, first, calm down." It sounds silly, but it was really helpful to hear. Then it went on to say, "Now, let's talk about some things. I'm hearing what you did do, but here are some things that maybe you could do that I'm not hearing." A research partner Some of its suggestions were unexpected. One was to make a cake for someone, because it was a company that appreciates bold moves. I don't know if that was really good advice, but it did come up with that. It would also suggest how to tailor a message to a particular person. Or, for example, to use email, not LinkedIn, because they're not active on LinkedIn — those sorts of tidbits. One of the taglines I've developed from my experience is that one way to think about AI is not as a tool but as the world's best expert in whatever you need help with. The more you leverage AI through that lens, the more you get out of it. I used it to create what's called a panel of experts. Now, you've got AI playing multiple roles at once. It can slice and dice and give you different views and a synthesized opinion. Another example is downloading the profile information for the person you're going to interview with. You can have AI assume the role of the interviewer and do a mock interview, and you can do it live with your voice, and then get feedback on how you performed. It also started calling out things like applying to incremental CEO roles. It recommended doing more cold outreach, which I hadn't leaned into too much. It helped me figure out a plan that worked for me and language that worked for me to do that, and it gave me concrete steps. 'You're missing it' The way that I ended up at Pearl is interesting. When I saw the job description, I passed it up because, on paper, it's different from anything I'd done before. Now it's laughable, because I'm in it, and everybody's connecting my passion and my past with the role. Maybe a week later, I saw the posting again and thought, "Why am I saying 'no' to myself? Let me just drop this thing into CareerBuddy GPT and see what it says. I didn't think that I was qualified, but I said, "Give me your objective assessment." It came back and said, "Hey, you're missing it. Your résumé doesn't speak to it, but here's how your experience aligns." It encouraged me to apply. So, then I did the network outreach, and I had a connection, which helped open the door. One thing led to the next. But what got me to apply was leveraging AI to the extent of not only answering, but also truly advising. I say trust, but verify. It told me to do something different than what I thought was right. I can represent me, what I am, and what I'm not. AI can look between the lines and challenge and question. When I was interviewing with our CEO, he asked me, toward the end of the interview, what my dream job was. I got about 15 to 20 seconds into stumbling around, and I said, "Look, I'm just going to be honest with you. I don't know how to spin this to make it sound good, because the honest answer is this: This job is my dream job." No more throwing darts After I started using AI, my job search still took a bit of time — maybe another five months or so. But I went from feeling like I was just throwing darts to where it felt much more targeted and precise. And, I'd gone from essentially getting no response to finding the right opportunities, having conversations, and it was a matter of finding the right fit. That can take time. We're in a moment when people and companies are about to be left behind, and I want to help that not be the case. The opportunity to go to a company that really gets it, is going after this full force, and wants to rewire with AI — that sounds like the hardest role of my career, but also the most fun and the most relevant thing I could be doing for this moment. So, not only did I stumble into the job, but I stumbled into my dream job.

Yahoo

36 minutes ago

• Yahoo

5 AI stocks to consider buying and holding for the long term

Many AI applications are still in development, offering ground-floor buying opportunities in their stocks. Below are some established companies that five of contract writers like as investments to consider buying to capitalise on this transformational technology. What it does: Alphabet is a global technology company best known for Google, YouTube, Android, and cloud services. By Mark Hartley. When considering an AI investment for the long term, Google's parent company Alphabet (NASDAQ: GOOG) stands out. It has emerged as a key player in the AI space, leveraging its vast data resources and computational power to dig deep roots into the industry. Through DeepMind and its Gemini AI models, Alphabet is at the forefront of generative AI development. Google Cloud offers scalable AI tools and infrastructure for businesses, while AI enhancements in products like Search, Gmail, and YouTube are well-positioned to benefit from advertising revenue. Alphabet's expansive ecosystem gives it a strategic advantage in training and deploying AI models at scale. A significant risk, however, lies in the potential disruption of its core search business. As AI chatbots and generative search become more prevalent, traditional search advertising could face margin pressure. Additionally, if faces increased regulatory scrutiny on data usage, antitrust concerns and competition from rivals like Microsoft and Amazon. Mark Hartley doesn't own shares in any of the stocks mentioned. What it does: Cellebrite is the global leader in decrypting mobile phones and other devices supporting digital forensic investigations. By Zaven Boyrazian. Many AI stocks today are unproven. That's why I prefer established players leveraging AI to improve their existing mission-critical products like Cellebrite (NASDAQ:CLBT). Cellebrite specialises in extracting encrypted data from mobile phones and other devices aiding law enforcement and enterprises in criminal and cybersecurity investigations. Over 90% of crime commited today has a digital element. And when it comes to decrypting mobile phones, Cellebrite is the global gold standard. The company is now leveraging AI to analyse encrypted data – drastically accelerating a task that's historically been increadibly labour intensive identifying patterns, discovering connections, and establishing leads. Most of Cellebrite's revenue comes from law enforcement, exposing Cellebrite to the risk of budget cuts. In fact, fears of lower US federal spending is why the stock dropped sharply in early 2025. And with a premium valuation, investors can expect more volatility moving forward. But in the long run, Cellebrite has what it takes to be an AI winner in my mind. That's why I've already bought shares. Zaven Boyrazian owns shares in Cellebrite. What it does: Dell Technologies provides a broad range of IT products and services and is an influential player in AI. By Royston Wild. Dell Technologies (NYSE:DELL) isn't one of the more fashionable names in the realm of artificial intelligence (AI). The good news is that this means it trades at a whopping discount to many of its peers. For this financial year (to January 2026), City analysts think earnings will soar 41% year on year, leaving it on a price-to-earnings (P/E) multiple of 12.6 times. Such readings are as rare as hen's teeth in the high-growth tech industry. In addition, Dell shares also trade on a price-to-earnings growth (PEG) ratio of 0.3 for this year. Any reading below 1 implies a share is undervalued. These modest readings fail to reflect the exceptional progress the company's making in AI, in my opinion. Indeed, Dell last month raised guidance for the current quarter as it announced 'unprecedented demand for our AI-optimised servers' during January-March. It booked $12.1bn in AI orders in the last quarter alone, beating the entire total for the last financial year. Dell is a major supplier of server infrastructure that let Nvidia's high-power chips do their thing. Dell's shares could sink if unfavourable developments in the ongoing tariff wars transpire. But the company's low valuation could help limit the scale of any falls. Royston Wild does not own shares in Dell or Nvidia. What it does: Salesforce is a customer relationship management (CRM) software company that is developing AI agents. By Edward Sheldon, CFA. We've all seen the potential of artificial intelligence (AI) in recent years. Using apps like ChatGPT and Gemini, we can do a lot of amazing things today. These apps are just the start of the AI story, however. I expect the next chapter to be about AI agents – software programmes that can complete tasks autonomously and increase business productivity exponentially. One company that is active in this space is Salesforce (NYSE: CRM). It's a CRM software company that has recently developed an agentic AI offering for businesses called 'Agentforce'. It's still early days here. But already the company is having a lot of success with this offering, having signed up 8,000 customers since the product's launch last October. Now, Salesforce is not the only company developing AI agents. So, competition from rivals is a risk. I like the fact that the company's software is already embedded in over 150,000 organisations worldwide though. This could potentially give it a major competitive advantage in the agentic AI race. Edward Sheldon has positions in Salesforce. What it does: Salesforce is a cloud-based software company specialising in customer relationship management, helping businesses manage sales, marketing, support, and data. By Ben McPoland. I think Salefsforce (NYSE: CRM) looks well set up to benefit in the age of AI. Specifically, its Agentforce platform, which lets businesses deploy AI agents to handle various tasks, could be the company's next big growth engine. By the end of April, it had already closed over 8,000 deals, just six months after launching Agentforce. Half of those were paid deals, taking its combined data cloud and AI annual recurring revenue above $1bn. Granted, that looks like small potatoes set against the $41.2bn in sales it's expected to generate this fiscal year. But it's still very early days, and management reckons the digital labour market opportunity could run into the trillions of dollars. Of course, it's always best to treat such mind-boggling projections with a healthy dose of scepticism. And the company does face stiff competition in the AI agent space, especially from Microsoft and ServiceNow. Nevertheless, I'm bullish here. Salesforce is already deeply embedded in sales, service, and marketing. Its AI agents slot into existing workflows, which I think will prove to be a big advantage over unproven AI upstarts. Ben McPoland owns shares of Salesforce. The post 5 AI stocks to consider buying and holding for the long term appeared first on The Motley Fool UK. More reading 5 Stocks For Trying To Build Wealth After 50 One Top Growth Stock from the Motley Fool John Mackey, former CEO of Whole Foods Market, an Amazon subsidiary, is a member of The Motley Fool's board of directors. Suzanne Frey, an executive at Alphabet, is a member of The Motley Fool's board of directors. The Motley Fool UK has recommended Alphabet, Amazon, Cellebrite, Microsoft, Nvidia, and Salesforce. Views expressed on the companies mentioned in this article are those of the writer and therefore may differ from the official recommendations we make in our subscription services such as Share Advisor, Hidden Winners and Pro. Here at The Motley Fool we believe that considering a diverse range of insights makes us better investors. Motley Fool UK 2025 Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data

Yahoo

40 minutes ago

• Yahoo

Franklin County home listings asked for more money in May - see the current median price here

The median home in Franklin County listed for $364,900 in May, up 1.2% from the previous month's $360,720, an analysis of data from shows. Compared to May 2024, the median home list price increased 13.2% from $324,723. The statistics in this article only pertain to houses listed for sale in Franklin County, not houses that were sold. Information on your local housing market, along with other useful community data, is available at Franklin County's median home was 1,968 square feet, listed at $183 per square foot. The price per square foot of homes for sale is up 2.2% from May 2024. Listings in Franklin County moved briskly, at a median 36 days listed compared to the May national median of 51 days on the market. In the previous month, homes had a median of 38 days on the market. Around 196 homes were newly listed on the market in May, a 7.7% increase from 182 new listings in May 2024. The median home prices issued by may exclude many, or even most, of a market's homes. The price and volume represent only single-family homes, condominiums or townhomes. They include existing homes, but exclude most new construction as well as pending and contingent sales. In Pennsylvania, median home prices were $325,000, a slight increase from April. The median Pennsylvania home listed for sale had 1,708 square feet, with a price of $196 per square foot. Throughout the United States, the median home price was $440,000, a slight increase from the month prior. The median American home for sale was listed at 1,840 square feet, with a price of $234 per square foot. The median home list price used in this report represents the midway point of all the houses or units listed over the given period of time. Experts say the median offers a more accurate view of what's happening in a market than the average list price, which would mean taking the sum of all listing prices then dividing by the number of homes sold. The average can be skewed by one particularly low or high price. The USA TODAY Network is publishing localized versions of this story on its news sites across the country, generated with data from Please leave any feedback or corrections for this story here. This story was written by Ozge Terzioglu. Our News Automation and AI team would like to hear from you. Take this survey and share your thoughts with us. This article originally appeared on Chambersburg Public Opinion: Franklin County home listings asked for more money in May - see the current median price here