News for hackers. Stuff that matters.
Re:Benchmarking GPT-4 Turbo – A Cautionary Tale by doug_durham on Thursday November 09, 2023 @03:20PM (#38210646)
Natural language isn't superior to computer languages. NL allows you to describe a software concept in a computer language and framework neutral way. The LLM generates the code. The real benefit is when you work across languages and frameworks. It is difficult to keep all of the details of all of the framework calls in your head all of the time.
Re:Benchmarking GPT-4 Turbo – A Cautionary Tale by gloosx on Friday November 10, 2023 @01:39AM (#38215816)
>NL allows to describe a software concept in a computer language

What does that even mean? Natural language allows to describe in computer language? This is nonsense. The concept is only superficial, and you develop all the details of it using code itself. To outsource this development for a black-box which can get 60% of the tasks correctly is to learn a lot, but to loose all of the details.

Re:Benchmarking GPT-4 Turbo – A Cautionary Tale by gloosx on Friday November 10, 2023 @01:57AM (#38215937)
Where is the evidence for that? Any real-world application made and running by describing software concepts to an LLM?

It is what it is – a novel search engine, lossy and non-credible. Effectively useless on codebases that extend beyond its fairly limited context