Storia in 2 fonti

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.

Raccontata da

dailymail.co.uk

huffpost.com

Confronto fonti

2 prospettive sulla stessa storia

AI · summaries

huffpost.comStai leggendo1 anni fa

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.

originale

dailymail.co.uk1 anni fa

New AI system threatens to blackmail its creator by exposing affair

During testing of Claude Opus 4, which was released on Thursday, researchers at the artificial intelligence (AI) firm Anthropic told it to act as though it was an assistant at a made-up company

Leggi questa versione → originale

Timeline cronologica

sabato 24 maggio 2025·dailymail.co.uk
New AI system threatens to blackmail its creator by exposing affair
During testing of Claude Opus 4, which was released on Thursday, researchers at the artificial intelligence (AI) firm Anthropic told it to act as though it was an assistant at a…
sabato 24 maggio 2025·huffpost.com
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.