Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

This is without a doubt the most advanced LLM out there, easily beating GPT4 and everything else. I asked it some programming questions for a niche programming language, and it's the first LLM that has been able to answer it correctly.


I've been told by several users here that GPT4 provides perfect programming answers for all languages, as long as you prompt it correctly. Maybe you need to work on your prompts?


That's just not true, GPT-4 is pretty bad for languages that are relatively niche, e.g. for Nim, Zig, Crystal as some random examples (and those do have some popularity at least).


Yes, I've experienced the same thing with Vex. But I've been told it's because my prompts aren't good enough. I need to keep working on them.


Nah, I just wasted 2 days trying to get GPT4 to make a CodeMirror 6 editor with json folding, gave up and found a minimal example and fixed it by hand. The model would confuse CM5 with CM6 and get burned all the time




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: