Get the latest tech news

Show HN: Prompting LLMs in Bash scripts

Of course it's that easy.

I’ve been ex­per­i­ment­ing with us­ing LLMs lo­cally for gen­er­at­ing datasets to test Harper against. I might write a blog post about the tech­nique (which I am grandiosely call­ing“LLM-assisted fuzzing”), but I’m go­ing to make you wait. For ex­am­ple, you can swap out the sys­tem prompt, so if you want to com­pare be­hav­ior across prompts, you can just toss it in a loop:

Get the Android app