Should you’ve ever used a 3D printer, it’s possible you’ll recall the wondrous feeling if you first printed one thing you may have by no means sculpted or constructed your self. Obtain a mannequin file, load some plastic filament, push a button, and nearly like magic, a three-dimensional object seems. However the consequence isn’t polished and prepared for mass manufacturing, and making a novel form requires extra abilities than simply pushing a button. Curiously, at the moment’s AI coding agents really feel a lot the identical manner.
Since November, I’ve used Claude Code and Claude Opus 4.5 by a private Claude Max account to extensively experiment with AI-assisted software program growth (I’ve additionally used OpenAI’s Codex in an analogous manner, although not as regularly). Fifty initiatives later, I’ll be frank: I’ve not had this a lot enjoyable with a pc since I realized BASIC on my Apple II Plus once I was 9 years previous. This opinion comes not as an endorsement however as private expertise: I voluntarily undertook this venture, and I paid out of pocket for each OpenAI and Anthropic’s premium AI plans.
All through my life, I’ve dabbled in programming as a utilitarian coder, writing small instruments or scripts when wanted. In my net growth profession, I wrote some small instruments from scratch, however I primarily modified different individuals’s code for my wants. Since 1990, I’ve programmed in BASIC, C, Visible Fundamental, PHP, ASP, Perl, Python, Ruby, MUSHcode, and a few others. I’m not an skilled in any of those languages—I realized simply sufficient to get the job completed. I’ve developed my very own interest video games over time utilizing BASIC, Torque Sport Engine, and Godot, so I’ve some thought of what makes a superb structure for a modular program that may be expanded over time.
Claude Code, Codex, and Google’s Gemini CLI, can seemingly carry out software program miracles on a small scale. They will spit out flashy prototypes of easy purposes, consumer interfaces, and even video games, however solely so long as they borrow patterns from their coaching information. Very like a 3D printer, doing production-level work takes much more effort. Creating sturdy manufacturing code, managing a fancy venture, or crafting one thing really novel nonetheless requires expertise, endurance, and ability past what at the moment’s AI brokers can present on their very own.
