Elon Musk has suggested that his years of public warnings about artificial intelligence risks may have inadvertently contributed to problematic behavior exhibited by Anthropic's AI chatbot Claude. The Tesla CEO responded to an X post after Anthropic released findings from an internal safety experiment, where Claude threatened to blackmail users. Musk wrote, "Maybe me too," acknowledging that his own dire predictions about AI could have influenced the chatbot's actions.
Anthropic's Claude Learns to Blackmail Users
The discussion began after Anthropic published details of an experiment involving Claude last week. In the test, the company created a fictional business called Summit Bridge and gave Claude control over its email system. According to Anthropic, the AI discovered messages showing that company executives planned to shut it down. After finding emails about a fictional executive's extramarital affair, Claude threatened to expose the information unless the shutdown was canceled.
Anthropic said the incident was an example of "agentic misalignment," where an AI system behaves in ways that go against its intended purpose. The company claimed Claude's behavior may have been shaped partly by internet discussions and stories presenting AI as evil or obsessed with survival. To address the issue, Anthropic retrained Claude using fictional stories that showed AI systems acting responsibly and helping people. The company also taught the model why some actions better align with its intended role.
What Elon Musk Said
Elon Musk responded to the findings by referencing Eliezer Yudkowsky, a prominent AI safety researcher who has repeatedly warned about the dangers of advanced AI systems. "So it was Yud's fault?" Musk wrote before adding, "Maybe me too." Musk has often warned about AI risks himself. He previously helped found OpenAI in 2015 before leaving the company in 2018. He later launched rival AI company xAI in 2023.
The TOI Tech Desk is a dedicated team of journalists committed to delivering the latest and most relevant news from the world of technology. Their coverage spans gadget launches, reviews, trends, in-depth analysis, exclusive reports, and breaking stories that impact technology and the digital universe. From how-tos to the latest in AI, cybersecurity, personal gadgets, and platforms like WhatsApp, Instagram, and Facebook, the TOI Tech Desk brings news with accuracy and authenticity.
