AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
How to Write Descriptions That Help the LN to Choose the Functions
The LN is responding up to 7000 tokens out of one single prompt. It's made to work off documentation, right? Like that's the key thing is that it has seen a lot of documentation. I would definitely add a function summary of what's there at the end of every prompt. So yeah, anyway, it doesn't look like an 8K in responses. You can dump in up to it. But we're going to have to build up and actually writing maybe as well.