News for hackers. Stuff that matters.

A comment on The art of programming and why I won't use LLM. Parent comment

Re:The art of programming and why I won't use LLM by computerex on Sunday August 25, 2024 @03:14PM (#41350305)
So what if the output is stochastic? LLM's have self consistency, so you can repeat the inference several times and pick the most frequent output.
[ Parent | on HN ]
Re:The art of programming and why I won't use LLM by dazilcher on Sunday August 25, 2024 @03:32PM (#41350511)
Most frequent output does not imply correctness, LLMs often are confidently wrong.

They can't even perform basic arithmetic (which is not surprising since they operate at the syntactic level, oblivious to any semantic rules), yet people seem to think offloading more complex tasks with strict correctness requirements is a good idea. Boggles the mind tbh.

[ Parent | on HN ]
Re:The art of programming and why I won't use LLM by saulpw on Sunday August 25, 2024 @03:18PM (#41350354)
And you can pay in time and/or $$ for the privilege of having to do do this extra unnecessary work.
[ Parent | on HN ]