Widening the conversation on frontier AI
… This raises questions about how the character of an AI system should be shaped: What does it mean for an AI to be good? Which traits and behaviors should it display, and under what circumstances? …
Search
Measuring AI agent autonomy in practice
… Among new users, roughly 20% of sessions use full auto-approve, which increases to over 40% as users gain experience. Claude Code pauses for clarification more often than humans interrupt it. …
Building Effective AI Agents
… Agents can then pause for human feedback at checkpoints or when encountering blockers. The task often terminates upon completion, but it’s also common to include stopping conditions such as a maximum number of iterations to maintain control. …
Introducing advanced tool use on the Claude Developer Platform
… Traditional approach: All tool definitions loaded upfront ~72K tokens for 50+ MCP tools Conversation history and system prompt compete for remaining space Total context consumption: ~77K tokens before any work begins With the Tool Search Tool: Only the Tool Search Tool loaded upfront ~500 tokens To… …