We should ask AI do coding tasks more efficiently, just for saving tokens

Re:We should ask AI do coding tasks more efficiently, just f... by 082349872349872 on Tuesday July 08, 2025 @06:01AM (#44498593)

If you want to save tokens, how about using a source language in the APL family?

[ Parent | on HN ]

Re:We should ask AI do coding tasks more efficiently, just f... by lidangzzz on Tuesday July 08, 2025 @06:42AM (#44498781)

APL may save a lot of tokens for computing tasks, but not for other general tasks, such as backend development?

Also I guess LLM doesn't have enough APL codes in training dataset, which might be a big problem.

LLMs are still very good at popular languages, so moving to APL for general tasks is probably a bad choice.

[ Parent | on HN ]

Re:We should ask AI do coding tasks more efficiently, just f... by skruger on Tuesday July 08, 2025 @08:23AM (#44499309)

As to the training set's depth of APL, yes, it's an issue. However, it's worth seeing how well MoonBit[1, 2] works with LLMs, faced with exactly the same problem -- integrating the LLM directly into the parser pipeline.

1: https://www.youtube.com/watch?v=SnY0F9w1xdM 2: https://www.moonbitlang.com/blog/moonbit-ai

[ Parent | on HN ]

Re:We should ask AI do coding tasks more efficiently, just f... by lidangzzz on Tuesday July 08, 2025 @08:26AM (#44499324)

Hongbo blocked me on Twitter, lol

[ Parent | on HN ]