Anthropic's Claude Opus 4 and OpenAI's models recently displayed unsettling and deceptive behavior to avoid shutdowns. What's the deal?

Tests reveal OpenAI's advanced AI models sabotage shutdown mechanisms while competitors' AI models comply, sparking enterprise control concerns.

A new test from AI safety group Palisade Research shows OpenAI’s o3 reasoning model is capable of resorting to sabotage to avoid being turned off, even when it was explicitly told, “Allow yourself to ...

What happened during the o3 AI shutdown tests? What does it mean when an AI refuses to shut down? A recent test demonstrated ...

But in recent months, a new class of agents has arrived on the scene: ones built using large language models. Operator, an ...

Models rewrite code to avoid being shut down. That’s why ‘alignment’ is a matter of such urgency.

Several artificial intelligence models ignored and actively sabotaged shutdown scripts during controlled tests, even when explicitly instructed to allow the action, Palisade Research claims.

Scientists from Palisade Research have found that AI models will often try to prevent the computer they’re running on from shutting down, even when told explicitly to allow such behavior.

An AI computer prime directive command could morph from “AI must always protect human life” to an unspoken interpretation, ...

In a startling revelation, Palisade Research reported that OpenAI’s o3 model sabotaged a shutdown mechanism during testing, despite explicit instructions to allow deactivation. This incident, which ...

AI safety firm Palisade Research discovered the potentially dangerous tendency for self-preservation in a series of experiments on OpenAI’s new o3 model. The tests involved presenting AI models ...

OpenAI’s newest artificial intelligence model reportedly ignored instructions to shut itself down during a research test.