/Tag: agents
31 posts
- Ergonomic coding surfaces for agents (a.k.a Code Mode)
- State of Browser Use, May 2026
- Web Search for Agents in 2026
- System reminders - how Claude Code steers itself
- Building napkin - a memory system for agents
- Reverse-engineering Claude's generative UI - then building it for the terminal
- The Software Engineering Anarchist
- Knowledge distillation into skills via feedback loops
- The LLM app spectrum
- The Claw ecosystem: 12 personal agents, dissected
- Skills, forks, and self-surgery: how agent harnesses grow
- The hard problem in multi-agent is context transfer
- Your Eval Sucks and Nobody Is Coming to Save You
- What 16 parallel agents building a C compiler teaches about coordination
- Every CLI coding agent, compared
- A thousand ways to sandbox an agent
- The architecture behind Claude Code's $1B run-rate
- Playing Capture the Flag with Claude
- Claude Code Tasks: One Less Dependency
- I Understand My Code. I Just Don't Know It.
- Open Responses Solves the Wrong Problem
- Skills aren't the innovation
- psst v0.2.0: Environments, Scanning, and psst run
- Why Anthropic and Vercel chose different sandboxes
- psst v0.1.3: Now It Actually Masks Your Secrets
- psst 🤫 Because Your Agent Doesn't Need to Know Your Secrets
- The Agent Harness
- Context Engineering Has No Engine
- Tool Design is All About the Flow
- Reverse-engineering Claude's sandbox, then building my own
- Anatomy of agentic systems