Comment by phkahler
6 days ago
>> Blaming LLM hallucinations on the programming language?
My favorite was suggesting that people select the programming language based of which ones LLMs are best at. People who need an LLM to write code might do that, but no experienced developer would. There are too many other legitimate considerations.
If an LLM improves coding productivity, and it is better at one language than another, then at the margin it will affect which language you may choose.
At the margin means that both languages, or frameworks or whatever, are reasonably appropriate for the task at hand. If you are writing firmware for a robot, then the LLM will be less helpful, and a language such as Python or JS which the LLM is good at is useless.
But Thomas's point is that arguing that LLMs are not useful for all languages is not the same as saying that are not useful for any language.
If you believe that LLM competencies are not actually becoming drivers in what web frameworks people are using, for example, you need to open your eyes and recognize what is happening instead of what you think should be happening.
(I write this as someone who prefers SvelteJS over React - but LLM's React output is much better. This has become kind of an issue over the last few years.)
I'm a little (not a lot) concerned that this will accelerate the adoption of languages and frameworks based on their popularity and bury away interesting new abstractions and approaches from unknown languages and frameworks.
Taking your react example, then if we we're a couple years ahead on LLMs, jQuery might now be the preferred tool due to AI adoption through consumption.
You can apply this to other fields too. It's quite possible that AIs will make movies, but the only reliably well produced ones will be superhero movies... (I'm exaggerating for effect)
Could AI be the next Cavendish banana? I'm probably being a bit silly though...
> I'm a little ... concerned that this will accelerate the adoption of languages and frameworks based on their popularity and bury away interesting new abstractions and approaches...
I'd argue that the Web development world has been choosing tooling based largely on popularity for like at least a decade now. I can't see how tooling selection could possibly get any worse for that section of the profession.
8 replies →
People make productivity arguments for using various languages all the time. Let's use an example near and dear to my heart: "Rust is not as productive as X, therefore, you should use X unless you must use Rust." If using LLMs makes Rust more productive than X, that changes this equation.
Feel free to substitute Y instead of Rust if you want, just I know that many people argue Rust is hard to use, so I feel the concreteness is a good place to start.
Maybe they don’t today, or up until recently, but I’d believe it will be a consideration for new projects.
Is certainly true that at least some projects choose languages based on or at least influenced by how easy it is to hire developers fluent in that language.