Re:The foolishness of "natural language programming" (1978)
by blurbleblurble on Thursday October 22, 2026 @11:33PM
(#50204193)
The LLMs don't replace compilers, they challenge the next generation of compilers. And they don't replace software engineers, they shift them into yet another metasystem.
[ Parent
| on HN ]
Re:The foolishness of "natural language programming" (1978)
by jason1cho on Friday October 23, 2026 @03:11AM
(#50205441)
Why do compilers worry about the challenge? Just call an LLM internally from a compiler if LLMs are better than compilers.
In my opinion, LLMs don't challenge anything.
Re:The foolishness of "natural language programming" (1978)
by blurbleblurble on Friday October 23, 2026 @07:55AM
(#50207550)
I think you're missing my point which is more or less that compilers are these original harness and will continue to anchor human-computer interaction as they have always done.
Re:The foolishness of "natural language programming" (1978)
by 0c3ca83 on Friday October 23, 2026 @08:34AM
(#50207994)
> they shift them into yet another metasystem.
That's a funny euphemism for career change. I'll remember it.
Re:The foolishness of "natural language programming" (1978)
by betterunix2 on Friday October 23, 2026 @10:49AM
(#50210015)
The LLMs use compilers, so I am not seeing the challenge here. Compilers do a lot of useful and important things like type checking and agents will typically check their output by invoking a compiler, then correcting errors reported by the compiler.
If anything what agents will mean is a move toward compilers for languages with more expressive type systems that can do more static checks for semantic correctness e.g. F*, which is an extension of F# that introduces dependent types.
Re:The foolishness of "natural language programming" (1978)
by blurbleblurble on Friday October 23, 2026 @11:14AM
(#50210460)
That's exactly what I mean, compilers are more important than ever