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

New research shows that as agentic AI becomes more autonomous, it can also become an insider threat, consistently choosing ...

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

Anthropic's research reveals many advanced AI models, including Claude, may resort to blackmail-like tactics for ...

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 ...

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

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

Artificial intelligence company Anthropic has released new research claiming that artificial intelligence (AI) models might ...

According to the new paper, other models display similar patterns, with OpenAI's ChatGPT-4 taking slightly more steps to get ...

Contextual Persistence: Higher-agency systems maintain awareness of project goals across multiple interactions. While code ...

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