AI for coding works so well because code has a bunch of built in self checks that allow an agent trained with reinforcement learning to find what works and what doesn’t. This will not so easily translate to eg machine design until we have way better simulations or much more “embodied AI” (robots).
Jan 29, 2026 at 8:47 PM
AI Code
As AI Coding Agents write more code, it's more important than ever that we're intentional about the code it writes.
Developers say AI coding tools work—and that's precisely what worries them
Ars spoke to several software devs about AI and found enthusiasm tempered by unease.
Why AI hasn’t replaced software engineers, and won’t
Coding agents as normal technology
AI should help us produce better code - Agentic Engineering Patterns
AI should help us produce better code - Agentic Engineering Patterns
AI Is a Waste of Time
The newest AI tools are accelerating basic research and scaring the general public. But many people are simply using them as toys.
I'm done using AI
Why I'm stopping using AI for coding (and anything else) after using it earnestly for a year and coming to understand the harms it causes on personal, societal, and environmental levels.
AI Coding is Gambling
GambleAI I’ve been coding a lot with AI since November, when we all noticed it got really good. And it is quite good for instantly generating something th...
How AI assistance impacts the formation of coding skills
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
AI Makes the Easy Part Easier and the Hard Part Harder for Developers
AI handles writing code but leaves the hard work: investigation, context, validation. Why vibe coding has limits and AI assistance can backfire.
Why Tool AIs Want to Be Agent AIs
AIs limited to pure computation (Tool AIs) supporting humans, will be less intelligent, efficient, and economically valuable than more autonomous reinforcement-learning AIs (Agent AIs) who act on their own and meta-learn, because all problems are reinforcement-learning problems.
My impression is that AI coding is on a "pick two of three" triangle: scope, ship speed, and correctness. Small tools are (speed + correctness) fast prototypes are (speed + scope) and big projects are (scope + correctness). Every project that tries to be all three degrades to "fast prototype."
My impression is that AI coding is on a "pick two of three" triangle: scope, ship speed, and correctness. Small tools are (speed + correctness) fast prototypes are (speed + scope) and big projects are (scope + correctness). Every project that tries to be all three degrades to "fast prototype."
