FeedSources
AE

Anthropic Engineering

6 articles total

Go to source

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

Go to source
  •  How we contain Claude across products
  •  An update on recent Claude Code quality reports
  •  Scaling Managed Agents: Decoupling the brain from the hands
  •  How we built Claude Code auto mode: a safer way to skip permissions
  •  Harness design for long-running application development
  •  Eval awareness in Claude Opus 4.6’s BrowseComp performance