New research on how we've reduced agentic misalignment
The Gap Through Which We Praise the Machine
My current theory of agentic programming: people are amazing at adapting the tools they're given and totally underestimate the extent to which they do it, and the amount of skill we build doing that is an incidental consequence of how badly the tools are designed.
How we built our multi-agent research system
On the the engineering challenges and lessons learned from building Claude's Research system
Agent Design Is Still Hard
My Agent abstractions keep breaking somewhere I don’t expect.
Agentic AI gets lost
On the failure of AI to develop world models
Writing code is cheap now - Agentic Engineering Patterns
Writing code is cheap now - Agentic Engineering Patterns
Skills, forks, and self-surgery: how agent harnesses grow
Claude Code, NanoClaw, and Pi take radically different approaches to harness extensibility. The tradeoff is always safety vs. agent agency.
Thoughts on slowing the fuck down
Mario Zechner created the Pi agent framework used by OpenClaw, giving considerable credibility to his opinions on current trends in agentic engineering. He's not impressed: We have basically given up …
Composing Action: Representative Agents and the Search for Viable Arrangements | shishyko!
Why promising ideas die between discovery and action, and how representative agents might help
Agent Skills
AI coding agents take the shortest path to done, which usually means skipping the specs, tests, and reviews that make software reliable at scale. Agent Skill...
Can agentic coding raise the quality bar?
Five examples of using agentic coding to improve software quality, instead of delivery throughput.
Agentic manual testing - Agentic Engineering Patterns
Agentic manual testing - Agentic Engineering Patterns