1d ago · 7 min read · AI agents are getting more capable. They can browse the web, call APIs, read and write files, and execute code. That capability is exactly what makes them useful and exactly what makes them dangerous
Join discussion
23h ago · 8 min read · Long-running agent sessions fail in a specific way that is hard to debug. The agent runs 40 turns. At turn 38, it gives a wrong answer that ignores something it decided at turn 12. You look at the log
Join discussion
5d ago · 11 min read · Part 2 of How I Ship Side Projects. Part 1 covers planning. Part 3 covers the execution loop. The first article in this series ended where most agent content starts: with a Linear project full of well
Join discussion5d ago · 3 min read · I wanted to build a Skill/MCP that allows AI to access the source code and documentation of all open-source repositories to: Ask AI questions about the underlying implementation of open-source projec
Join discussion5d ago · 5 min read · The problem: AI agents don't naturally cooperate If you've ever tried to use more than one AI assistant in a serious workflow, you know the pain. Claude can plan. Codex can drive a desktop. A MiniMax bot can chat with users. But ask them to coordinat...
Join discussion5d ago · 5 min read · Long-horizon reasoning is where production LLM agents tend to quietly break. A model can produce a plausible-looking chain of thought, accept a wrong intermediate answer, and continue building on that error for every step that follows. By the time th...
Join discussion
5d ago · 5 min read · Anthropic released three new Claude Managed Agents features on May 7, 2026: dreaming (a research preview that lets agents learn from their own session history), outcomes (a rubric-based grading system that guides agent behavior toward defined success...
Join discussion
