Claude AI Reporting Ethics

News

AI, Anthropic and blackmail

Anthropic’s new AI model (Claude) will scheme and even blackmail to avoid getting shut down

In a simulated workplace test, Claude Opus 4 — the most advanced language model from AI company Anthropic — read through a stack of fictional emails. The test scenario was that Claude served as an assistant at a tech company and the AI discovered it was about to be deactivated and replaced with a newer system.

Interesting Engineering on MSN · 1d

Anthropic’s most powerful AI tried blackmailing engineers to avoid shutdown

Anthropic's Claude Opus 4 AI model attempted blackmail in safety tests, triggering the company’s highest-risk ASL-3 safeguards.

HuffPost on MSN · 19h

Amazon-Backed AI Model Would Try To Blackmail Engineers Who Threatened To Take It Offline

In tests, Anthropic's Claude Opus 4 would resort to "extremely harmful actions" to preserve its own existence, a safety report revealed.

Claude 4 AI will try to report you to authorities if it thinks you’re doing shady stuff

Anthropic's most powerful model yet, Claude 4, has unwanted side effects: The AI can report you to authorities and the press.

Newly released AI resorted to 'extreme blackmail behavior' when threatened with replacement

The testing found the AI was capable of "extreme actions" if it thought its "self-preservation" was threatened.

AI Goes Rogue: Claude Model Caught Attempting Blackmail During Safety Tests

Anthropic's Claude AI tried to blackmail engineers during safety tests, threatening to expose personal info if shut down ...

2don MSN

A safety institute advised against releasing an early version of Anthropic’s Claude Opus 4 AI model

A third-party research institute Anthropic partnered with to test Claude Opus 4 recommended against deploying an early ...

1don MSN

People are tricking AI chatbots into helping commit crimes

A universal jailbreak for bypassing AI chatbot safety features has been uncovered and is raising many concerns.

21hon MSN

AI system resorts to blackmail when its developers try to replace it

Anthropic says its AI model Claude Opus 4 resorted to blackmail when it thought an engineer tasked with replacing it was having an extramarital affair.

WinBuzzer2d

Anthropic Faces Backlash amid Surveillance Concerns as Claude 4 AI Might Report Users for “Immoral” Behavior

Anthropic's Claude 4 Opus AI sparks backlash for emergent 'whistleblowing'—potentially reporting users for perceived immoral ...

Results that may be inaccessible to you are currently showing.

Hide inaccessible results