Anthropic blocks attempt to develop weapons software using AI model
Community Score: 50% | 1.4K views | 4w
0 community ratings: null thumbs up, null thumbs down
Anthropic says it managed to block an attempt to use its AI model to develop biological weapons. The firm published its latest threat intelligence report detailing attempts at "malicious activity", and warned that, without safeguards, attempts at biological misuse "could have catastrophic consequences". In six cases, the Claude AI model was also used to try to develop software for conventional missiles and armed drones. [Subscribe to our Substack newsletter: https://channel4news.substack.com/subscribe] ------- Get more news at our site - https://www.channel4.com/news/ Subscribe to our Substack newsletter: https://channel4news.substack.com/subscribe Follow us: TikTok - https://www.tiktok.com/@c4news Instagram - https://www.instagram.com/channel4news/ Twitter - https://twitter.com/Channel4News Facebook - https://www.facebook.com/Channel4News/
Tags: Channel 4 News, latest news, world news, international news, UK News
More from Channel 4 News
- Andrew Mountbatten-Windsor’s arrest explained — Score: 50%
- All but one of charged Palestine Action activists released on bail — Score: 50%
- UK government considers removing Andrew from line of succession — Score: 50%
- US Supreme Court rules against Trump’s ‘Liberation Day’ tariffs — Score: 50%
- Epstein Files: Andrew arrested and missing data - this is still the beginning — Score: 50%
- Thai Police dress as lion dancers to catch alleged thief — Score: 50%