Hacker News Front Page · mfrw ·
What agents mean for Rust (and vice versa)
El artículo sostiene que Rust encaja bien con el desarrollo asistido por agentes porque combina buen rendimiento predeterminado con controles para optimizar y un sistema de tipos que ayuda a evitar errores. Propone reforzar esas ventajas haciendo el sistema de tipos más expresivo, integrando mejor las herramientas de prueba formal y permitiendo demostrar que el código `unsafe` es seguro. También plantea que, a medida que los agentes escriban más código, las personas y las herramientas deberán centrarse más en especificar y revisar el diseño.
As someone who has made a career of programming language design, I definitely have moments of existential dread about the rise of LLMs. I started coding in 5th grade on an x861 that ran at 5MHz, had something like a 5MB hard-disk and 512K of RAM2. Computers were really, really different back then. But honestly, programming wasn’t. For all the advances in IDEs and programming languages and so forth, the basic act of entering code into a file has remained surprisingly constant3 – right up until a few years ago, when everything kinda turned on its head. That’s been exciting and empowering at times4 but also scary and disorienting. Will my skills in programming matter? What about my skills in programming language design (such as they are)? This blog post is my attempt to answer those questions.