The Smallest Reliable Working Set
AI agents suffer from context overload much like software experiences memory leaks. Adding more RAM or expanding a model’s context window often masks the real issue: too much irrelevant information in the working set. Effective agents keep prompts focused, streaming only the files or data needed for the current task while storing durable knowledge separately. This disciplined separation mirrors best practices in system design and improves reliability.
I Deleted Todoist. I Built This Instead
The author replaced Todoist with a custom AI agent that handles task creation, retrieval, and daily briefings via natural language. By eliminating UI friction, the agent captures tasks in seconds and provides instant, contextual overviews, addressing common failures of traditional...
AI Agents Building Blocks
The author claims to have merged over a hundred Amazon pull requests last month without writing a single line of code, thanks to self‑built autonomous AI agents. He argues that merely using AI leads to excessive context‑switching and “AI slop,”...
How to Design a Career that Serves Your Life
The post challenges the conventional belief that career success equals climbing the corporate ladder, arguing that developers can design work paths that align with personal priorities. It contrasts the high‑intensity pursuit of titles, like Principal Engineer, with alternative routes such...