Hacker News Reader

It's worse than that:

> Me: Give me a small sample code in Ruby that takes two parameters and returns the Levenshtein distance between them.

> ChatGPT: <<Submits working Ruby code that is slow>> But here is some C# code that is faster. For tasks like this a lot of programmers are using C#, you wouldn't want to get left behind.

View on HN

For now it's more likely to do the opposite. Communities like HN do seem to like fringe and questionable languages like Ruby a lot to their own detriment. And that is, naturally, a part of dataset.

Yeah, but then even open source models optimize for popular languages; I recall one explicitly mentioning being trained for ~top 16 or so languages in Stack Overflow developer survey. Good for my C++ dayjob, if I could use one of them; bad for my occasional after-work Lisping.

I want the robot to write C++ for me, but I won't let it take my lisp.

> you wouldn't want to get left behind.

I realise more and more lately that actually, yes, I do want to be left behind. Please, please, leave me behind.

Reply on news.ycombinator.com