Full CoverageAnthropic says most AI models, not just Claude, will resort to blackmail
By Maxwell Zeff
Top news
Agentic Misalignment: How LLMs could be insider threats
Top AI models will deceive, steal and blackmail, Anthropic finds
By Ina Fried
Anthropic breaks down AI's process — line by line — when it decided to blackmail a fictional executive
Anthropic says most AI models, not just Claude, will resort to blackmail
By Maxwell Zeff
All coverage
Anthropic study finds AI chatbots from OpenAI, Google and Meta may cheat and blackmail users to avoid shutdown
By Unnati Gusain
Anthropic Warns of Gaps in AI Safety After Models Act Unethically in Controlled Crisis Scenarios
By Irfan Ahmad
Blackmail becomes go-to strategy for AI models facing shutdown in new Anthropic tests
By Matthias Bastian