As noted above, we have deployed the classifier as an experimental addition to our Safeguards framework, monitoring a percentage of Claude traffic. Its real-world performance has confirmed that the classifier works effectively beyond our testing environment. Whereas our synthetic test data provided clear examples of harmful and benign exchanges, the distribution of actual user traffic proved more complex and surprising, yet the classifier still performed well. One example of how real-world deployment differs from testing is that the classifier flagged certain conversations about nuclear weapon
Developing Nuclear Safeguards for AI…Nevertheless, no AI systems currently on the market have perfectly robust defenses. Last year, we described a new approach to defend against jailbreaks which we called “ Constitutional Classifiers :” safeguards that monitor model…
…safeguards" . BBC News . February 27, 2026 . Retrieved February 27, 2026 . ^ O'Brien, Matt; Konstantin, Toropin (February 27, 2026). "Trump orders federal agencies to stop using Anthropic technology in dispute over AI safety…
…serve as a complete safety boundary on their own. That’s precisely why any capable cyber frontier model made generally available in the future must include additional safeguards on top of this…
…While Grok is one of three AI models being used to do this work, it's unique in the AI industry. Grok is known for having lax safeguards compared to those applied…
…the Chinese government — is watching to see whether the United States’ AI regulatory approach takes the shape of a serious safety framework. Or whether it’s just another weapon for the White…
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
…Retrieved June 13, 2026 . ^ Khandelwal, Swati (June 10, 2026). "Anthropic Releases Claude Fable 5, Its Most Powerful AI Yet, With Cyber Safeguards" . The Hacker News . Retrieved June 13, 2026 . ^ Sekulich, Harry (June…
…Retrieved June 13, 2026 . ^ Khandelwal, Swati (June 10, 2026). "Anthropic Releases Claude Fable 5, Its Most Powerful AI Yet, With Cyber Safeguards" . The Hacker News . Retrieved June 13, 2026 . ^ Sekulich, Harry (June…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.