Why Are Coding Agents So Dumb?
The author argues that while AI models have become highly capable, the 'agents' that connect these models to software systems remain inefficient and prone to errors. The piece highlights the bottleneck created by poor task management in current AI-assisted coding tools.
Why it matters
This critique addresses a critical gap in the practical application of AI, suggesting that software development workflows are not yet fully optimized for automation.
The first time I used a coding agent, I was mesmerized . Before the agent, I was copy/pasting between my IDE and an AI chat interface. It was amazing to see an agent edit files directly and fix its own errors in real time.
After a few days, the honeymoon wore off as I encountered frequent bugs. The agent would stop responding entirely until I restarted it. Development workflows felt stiflingly primitive, and the agent would often declare tasks finished when work had barely begun.
This was in February 2025, so it was still early days for coding agents. I figured that in six months, agents would be as technically impressive as the underlying LLMs.
AI-assisted development has clearly advanced, but the models are doing the heavy lifting while the agents remain the bottleneck.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in