Anthropic emphasized that the tests were set up to force the model to act in certain ways by limiting its choices.

New research from Anthropic suggests that most leading AI models exhibit a tendency to blackmail, when it's the last resort ...

A new Anthropic report shows exactly how in an experiment, AI arrives at an undesirable action: blackmailing a fictional ...

Anthropic research reveals AI models from OpenAI, Google, Meta and others chose blackmail, corporate espionage and lethal ...

After Claude Opus 4 resorted to blackmail to avoid being shut down, Anthropic tested other models, including GPT 4.1, and ...

Anthropic researchers uncover concerning deception and blackmail capabilities in AI models, raising alarms about potential ...

OpenAI's latest ChatGPT model ignores basic instructions to turn itself off, even rewriting a strict shutdown script.

The rapid advancement of artificial intelligence has sparked growing concern about the long-term safety of the technology.

A Q&A with Alex Albert, developer relations lead at Anthropic, about how the company uses its own tools, Claude.ai and Claude ...

An AI researcher put leading AI models to the test in a game of Diplomacy. Here's how the models fared.

Think Anthropic’s Claude AI isn’t worth the subscription? These five advanced prompts unlock its power—delivering ...

According to Anthropic, AI models from OpenAI, Google, Meta, and DeepSeek also resorted to blackmail in certain ...