Coding is solved
Summary
The author observes that AI has increasingly made coding a solved problem.
Similar Articles
Coding is solved? Software is not.
The article argues that while AI coding tools have made implementation faster, software development remains complex because it involves turning ambiguous intent into reliable systems, a process that coding alone cannot solve.
Any example of code that AI cannot tackle?
A discussion questioning whether there is any code that AI cannot handle, noting that even difficult coding interviews at Anthropic are solvable by their own AI.
coding is basically solved for the boring 90% of tasks
A developer shares experience using cheap AI models (DeepSeek v4, Hunyuan Hy3 preview) to automate 90% of coding tasks, with Opus reserved for the harder 10%, highlighting cost and latency trade-offs.
On AI
The author reflects on his journey from manually typing code on a vintage Macintosh to embracing AI-powered code completion tools like Copilot and Claude, concluding that while the AI industry is problematic, the technology itself can be useful.
ai literally never makes mistakes anymore
The author claims AI coding agents no longer make mistakes, as they self-correct with linting and chain-of-thought, and asks if others agree.