Reflections on AI-Assisted Coding: Returning to Manual Programming After Two Years
By
mobitar
Lightly browned and well buttered. A solid pick from the rack.
Summary
The article reflects on the author's two-year experience with AI-assisted coding (vibecoding) and their decision to return to writing code manually. It describes the typical progression of AI coding adoption: initial excitement over simple tasks, amazement at handling larger projects, concerns about job displacement, and eventual realization of AI's limitations. The author notes that serious engineers using AI for real work follow a predictable development arc, but ultimately finds that AI agents produce code that looks good in isolation but lacks respect for the whole system's architecture and coherence.
Key quotes
· 4 pulledMost people's journey with AI coding starts the same: you give it a simple task. You're impressed. So you give it a large task. You're even more impressed.
If you've persisted past this point: congratulations, you understand AI coding better than 99% of people.
Serious engineers using AI to do real work and not just weekend projects largely also follow a predictable development arc.
Agents write units of changes that look good in isolation. They are consistent with themselves and your prompt. But respect for the whole, there is not.
You might also wanna read

AI's Impact on Software Engineering: Evolution or Replacement?
The article explores the complex relationship between AI tools like ChatGPT and software engineering, examining whether AI represents the en
How I Used Coding Agents to Automate My AI Research Work in Copilot Applied Science
An AI researcher shares their experience using coding agents to automate intellectual work, specifically building agents that automate parts
Building a Software Factory with Claude Code: From AI-Assisted Coding to Agentic Development
This article provides a comprehensive guide on building a software factory using Claude Code and other AI coding tools. It covers the evolut

Practical Guide to Using AI Coding Tools for Responsible Development
The article provides practical guidance for developers on responsibly integrating AI coding tools into their workflow. Based on two years of
How AI coding agents are reshaping social science research: Opportunities and concerns
This article examines how AI coding agents are transforming social science research by automating core research tasks traditionally performe

The Intensifying Competition in AI-Powered Coding Tools and Software Development
The article discusses the intensifying competition in AI-powered coding tools, focusing on how major tech companies like OpenAI, Google, and
