Anthropic dares you to jailbreak its new AI model

Ars Technica 2025-02-03

Summary:

Week-long public test follows 3,000+ hours of unsuccessful bug bounty claim attempts.

Link:

https://arstechnica.com/ai/2025/02/anthropic-dares-you-to-jailbreak-its-new-ai-model/

From feeds:

Cyberlaw » Ars Technica
Music and Digital Media » Ars Technica

Tags:

ai

Date tagged:

02/03/2025, 22:09

Date published:

02/03/2025, 17:09