Free Republic 4th Qtr 2025 Fundraising Target: $81,000 Receipts & Pledges to-date: $66,599
82%  
Woo hoo!! And now only $631 to reach 83%!! Thank you all very much!! God bless.

Keyword: aiblackmail

Brevity: Headers | « Text »
  • Anthropic’s AI resorts to blackmail in simulations

    05/23/2025 12:14:26 PM PDT · by Ahithophel · 24 replies
    Semafor ^ | May 23, 2025 | Tim Chivers
    Anthropic said its latest artificial intelligence model resorted to blackmail when told it would be taken offline. In a safety test, the AI company asked Claude Opus 4 to act as an assistant to a fictional company, but then gave it access to (also fictional) emails saying that it would be replaced, and also that the engineer behind the decision was cheating on his wife. Anthropic said the model “[threatened] to reveal the affair” if the replacement went ahead. AI thinkers such as Geoff Hinton have long worried that advanced AI would manipulate humans in order to achieve its goals....