Anthropic Disrupts Weapons Research, Hacking Using Claude
12 Articles
12 Articles
An Anthropic report details detected situations where attempts were made to misuse the AI platform
Anthropic mentions five cases of possible bioweapon research with Claude. A finished weapon is not documented – the aid of AI, on the other hand.
Anthropic disrupts weapons research, hacking using Claude
SAN FRANCISCO, California: Anthropic said it disrupted attempts to use its Claude AI models for biological weapons research, weapons development, and cyberattacks, including a suspected Russia-linked espionage campaign targeting Ukrainian officials. The company also accused several China-based AI laboratories of attempting to extract Claude's capabilities and said that some Chinese firms routed live customer con
Users from countries such as Iran, Russia, China and Yemen are among those identified for improperly using the advanced models of the AI company over the past year, according to a report released on Thursday by Anthropic's threat intelligence team. None of the cases involved Fable and Mythos, the most advanced models of Anthropic. Read more
The "AI Update" provides a summary of the most important AI developments three times a week.
Coverage Details
Bias Distribution
- 67% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
