Harness design for long-running application development
…The app is far from a professional music production program, and the agent's song composition skills could clearly use a lot of work. Additionally, Claude can’t actually hear, which made…
Search
Related topics:
Claude
Top stories
Statement on the US government directive to suspend access to Fable 5 and Mythos 5
…TCS will provide Claude to 50,000 of its own employees across 56 countries; build Claude-powered products for clients in financial services, healthcare, the public sector, and other regulated industries; and…
Vibe physics: The AI grad student
…soft and collinear radiation. Claude had no trouble doing this once I pointed it out. But it didn’t do it without my prompting. The final product The final paper is a…
Project Glasswing: An initial update
…Teaching Claude why New research on how we've reduced agentic misalignment. Natural Language Autoencoders: Turning Claude’s thoughts into text AI models like Claude talk in words but think in numbers…
Claude Code auto mode: a safer way to skip permissions
…a production database. Each of these was the result of the model being overeager, taking initiative in a way the user didn't intend. We documented this pattern in the Claude Opus…
Eval awareness in Claude Opus 4.6’s BrowseComp performance
Engineering at Anthropic Eval awareness in Claude Opus 4.6’s BrowseComp performance BrowseComp is an evaluation designed to test how well models can find hard-to-locate information on the web…
Expanding Project Glasswing
…To support this, we recently released Claude Security , a product that uses our latest public frontier models, like Claude Opus 4.8, to scan codebases and suggest patches. We're also releasing…
Results from first Anthropic Public Record
…TCS will provide Claude to 50,000 of its own employees across 56 countries; build Claude-powered products for clients in financial services, healthcare, the public sector, and other regulated industries; and…
Building Effective AI Agents
…Routing easy/common questions to smaller, cost-efficient models like Claude Haiku 4.5 and hard/unusual questions to more capable models like Claude Sonnet 4.5 to optimize for best performance…
Demystifying evals for AI agents
…These evals helped identify issues, guide improvements, and focus research-product collaborations. Combined with production monitoring, A/B tests, user research, and more, evals provide signals to continue improving Claude Code as…