G
23

Just hit 1,000 test prompts on a local LLM I'm fine-tuning for recipe generation...

I ran 1,042 prompts through a tiny 7B model I tweaked for turning pantry leftovers into dinner ideas, and it finally spit out a usable chili recipe that wasn't just beans and sadness.
2 comments

Log in to join the discussion

Log In
2 Comments
davidwright
Honestly thought AI cooking was a gimmick but this actually sounds promising.
2
gray_nelson
Yeah I was skeptical too @davidwright but it's wild how precise it can be with timing and temperature. The tracking alone makes it worth trying out.
7