Natural Language Autoencoders
…We’ve already applied NLAs to understand what Claude is thinking and to improve Claude’s safety and reliability. For instance: When Claude Opus 4.6 and Mythos Preview were undergoing safety…
Search
Claude Opus 4.6
…It plans more carefully, sustains agentic tasks for longer, can operate more reliably in larger codebases, and has better code review and debugging skills to catch its own mistakes. And, in a…
Demystifying evals for AI agents
…They evolved from manual grading to LLM graders with criteria defined by the product team and periodic human calibration, and now regularly run two separate suites for quality benchmarking and regression testing…
Anthropic Economic Index report: Economic primitives
…That these relationships are intuitive and consistent suggests the primitives capture relevant aspects of how people and businesses use Claude. External benchmarks reinforce this. In our productivity work , Claude’s time estimates…
Partnering with Mozilla to improve Firefox’s security
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Automated Alignment Researchers: Using large language models to scale scalable oversight
…We do this because we need a way to automatically and reliably evaluate whether the AAR has made progress. However, if AARs discovered much better weak-to-strong supervision methods that generalized…
Building Effective AI Agents
…Agents Agents are emerging in production as LLMs mature in key capabilities—understanding complex inputs, engaging in reasoning and planning, using tools reliably, and recovering from errors. Agents begin their work with…
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.