News for hackers. Stuff that matters.

A comment on If Claude Fable stops helping you, you'll never know. Parent comment

Re:If Claude Fable stops helping you, you'll never know by drowsspa on Tuesday June 09, 2026 @07:55PM (#48469441)
Would be nice if people published the prompts, thoughts and responses of the LLMs together with the code, in order to fight against these restrictions... Instead of just publishing the final result and talking vaguely about how they prompted the LLM in a Hacker news comment or Twitter thread

If LLMs are the new compilers those are the actual source code

[ Parent | on HN ]
Re:If Claude Fable stops helping you, you'll never know by soraminazuki on Tuesday June 09, 2026 @08:13PM (#48469558)
Agreed with the need for transparency, but LLMs are anything but compilers. Compilers, by definition, produce semantically equivalent code from one language to another. If a tool's output lacks any defined semantics, it isn’t a compiler. Because how good is a "compiler" whose outputs are entirely undefined behavior?
[ Parent | on HN ]
Re:If Claude Fable stops helping you, you'll never know by warkdarrior on Tuesday June 09, 2026 @10:24PM (#48470573)
> If a tool's output lacks any defined semantics, it isn’t a compiler.

Are you claiming that the natural language of the LLM output (e.g., English, Chinese) does not have semantics?? Someone should tell all the people cited at https://en.wikipedia.org/wiki/Formal_semantics_(natural_lang...

[ Parent | on HN ]
Re:If Claude Fable stops helping you, you'll never know by soraminazuki on Tuesday June 09, 2026 @11:06PM (#48470904)
If you have to conflate programming language theory with linguistics to make an argument, it's not a good argument.

Because you can strawman all you want, but you can't change the fact that there's no well defined behavior regarding what happens when you instruct LLMs to make a program that calculates 2 + 2. What's stopping it from creating index.html with 5 in it as a response?

[ Parent | on HN ]