Effective harnesses for long-running agents
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Prompting best practices
docs.claude.comComprehensive guide to prompt engineering techniques for Claude's latest models, covering clarity, examples, XML structuring, thinking, and agentic systems.
Refactoring the GPU Selector App with Claude Code: A Vibe Coding Experiment
I rebuilt my deep learning GPU selector app using Claude Code, and here is what I learned from this small vibe coding experiment.
Hidden Technical Debt of AI Systems: Agent Harness
The agent is the model plus the harness. The runtime is where the harness lives. As models get better, the structure we put around them turns from scaffoldin...
Effective harnesses for long-running agents
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Unsupervised Learning NO. 509
Google Approach to Stopping Prompt Injection, Response to Cory Doctorow's Latest Book/Talk, AI Persuasion Risk, Screens Most Interesting Thing to Kids, and more...