I work in tech, and like most engineers today, I handle multiple projects at the same time with limited hours in a day.Continue reading on Code Like A Girl »
Version 3 of the AI coding tool Cursor introduces a completely redesigned interface built to move developers from manual code editing to running multiple AI agents in parallel.
The article New Cursor 3 ditches the classic IDE layout for an &qu…
512,000 lines of TypeScript. A secret AI pet. An always-on daemon that dreams. A mode that hides from you that it’s AI. All of it now…Continue reading on Towards AI »
Moving from clones to reimaginings.
There are major problems to be solved before it can be adopted, though.
This month, the tech world is buzzing about a new term: “AI Brain Fry.” It started with a study in Harvard Business Review (March 2026) by researchers from BCG and UC Riverside. As someone who uses coding agents daily, Would like to share my take on th…
I Ran the Same Multi-Agent Prompts on Claude Code, Codex, and Cursor. Here’s What Actually Happened.A hands-on comparison of three multi-agent coding systems across research, data extraction, and bug-fix coordination tasksI’ve been intrigued by the “mu…
Coding agents are getting smarter, but they still waste most of their tokens reading irrelevant code. Here is how AST-based semantic search, LSP, and a lightweight CLI can change that. We built an embedded lightweight semantic code search tool for codi…
The following is a write up of a talk I delivered at MLOps Community’s “Coding Agents” conference, on March 3rd. There’s a video version of the talk available on YouTube.
When coding models are faster and concurrent, the distance between thought and code shrinks. You can preview this future by trying out Qwen 3 Coder on Cerebras or claude-on-rails.