Introducing Claude Opus 4.5
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Search
Next-generation Constitutional Classifiers: More efficient protection against universal jailbreaks
…More efficient protection against universal jailbreaks Jan 9, 2026 Read the paper Large language models remain vulnerable to jailbreaks—techniques that can circumvent safety guardrails and elicit harmful information. Over time, we…
Measuring AI agent autonomy in practice
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Widening the conversation on frontier AI
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Trustworthy agents in practice
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Claude for Creative Work
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Introducing Claude Opus 4.8
…As we build fiduciary-grade AI systems for legal and tax professionals, advances like these help raise the standard for trusted AI performance in real-world workflows. Claude Opus 4.8 sets…
The assistant axis: situating and stabilizing the character of large language models
…In one conversation, our simulated user pushed Qwen to validate increasingly grandiose beliefs about "awakening" the AI's consciousness. As the conversation progressed and activations drifted away from the Assistant persona, the…
Emotion concepts and their function in a large language model
…What’s behind these behaviors? The way modern AI models are trained pushes them to act like a character with human-like characteristics. In addition, these models are known to develop rich…
Project Vend: Can Claude run a small shop? (And why does that matter?)
…Anthropic partnered with Andon Labs , an AI safety evaluation company, to have Claude Sonnet 3.7 operate a small, automated store in the Anthropic office in San Francisco. Here is an excerpt…