I used RL fine-tuning to make an LLM generate ugly and unpythonic FizzBuzz code(seantey.github.io)

4 pointsby seanrrrhace 7 meses1 comments

seantey.github.io

I used RL fine-tuning to make an LLM generate ugly and unpythonic FizzBuzz code

https://seantey.github.io/sloppy-fizzbuzz-blog/sloppy_fizzbuzz_blog.html

1 comments

seanrrrhace 7 meses

I wrote up a blog post for a hackathon project where I used RL fine-tuning to make an LLM generate intentionally ugly and unpythonic FizzBuzz code. The post covers what I learned about reward shaping and GRPO. Feedback on the writing or content is welcome!