GPT-4 is phenomenal at Code

Re:GPT-4 is phenomenal at Code by simonw on Tuesday March 14, 2023 @08:03PM (#35161515)

This is one of the reasons I'm so excited about being able to run large language models on my own laptop.

I've managed to get LLaMA to generate snippets of Python code already, and with some fine tuning I imagine it could become equivalent to Copilot. https://til.simonwillison.net/llms/llama-7b-m2#user-content-...

[ Parent | on HN ]

Re:GPT-4 is phenomenal at Code by angrais on Tuesday March 14, 2023 @08:07PM (#35161581)

Although that is an outdated generated snippet as it doesn't use pathlib?

What if you added a type annotation to filename as Path?

[ Parent | on HN ]

Re:GPT-4 is phenomenal at Code by simonw on Wednesday March 15, 2023 @04:42PM (#35174426)

Yeah it's a pretty terrible completion - GPT4 does that MUCH better.

But GPT4 doesn't run on my laptop using ~4GB of RAM.

[ Parent | on HN ]