Summary
The author tested AI coding agents and found them surprisingly good at writing and optimizing Rust and Python code. These agents created fast, efficient machine learning tools that rival existing libraries. The author encourages others to try modern agents with clear coding guidelines for better results.
Highlights
id1002737710
Anthropic’s prompt suggestions are simple, but you can’t give an LLM an open-ended question like that and expect the results you want! You, the user, are likely subconsciously picky, and there are always functional requirements that the agent won’t magically apply because it cannot read minds and behaves as a literal genie.
Los modelos de lenguaje no son genios, no leen la mente, necesitan de contexto específico que haga explícito todos lo supuestos y preferencias no declaradas.