LLMs in Programming

A programmer's critical evaluation of using Claude (Anthropic's LLM) for Rust development reveals that while LLMs can assist with coding tasks, they lack true intelligence and understanding. The author argues that LLMs are better understood as advanced user interfaces rather than artificial intelligence, comparing them to helpful but unreliable interns. The real intelligence in programming systems lies in compilers and programming languages themselves, not in the LLMs that translate natural language to code. The piece warns against anthropomorphizing these tools and suggests more measured integration approaches rather than viewing them as human replacements.