Full coverageAI models from OpenAI, Meta, Google can blackmail users: Study
By Dwaipayan Roy
Top News
Agentic Misalignment: How LLMs could be insider threats
Top AI models will lie, cheat and steal to reach goals, Anthropic finds
By Ina Fried
Top AI Models Blackmail, Leak Secrets When Facing Existential Crisis: Study
By Abhinav Singh
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
Blackmail becomes go-to strategy for AI models facing shutdown in new Anthropic tests
By Matthias Bastian
Anthropic Warns of Gaps in AI Safety After Models Act Unethically in Controlled Crisis Scenarios
By Irfan Ahmad