Nothing so fancy. I just made a little python script to prompt the first model, wait for a response, then prompt the next model with the initial prompt + the response, and so on. It was very hacky and slow.
Oh neat. Yeah, if something like that had existed (and I’d been aware of it) I probably would have used it instead of building my own shoestring version.
Did you use OWUIs native “call simultaneous models to answer” feature for that or one of the AI debate harnesses?
Nothing so fancy. I just made a little python script to prompt the first model, wait for a response, then prompt the next model with the initial prompt + the response, and so on. It was very hacky and slow.
Ah - I thought you might have used something like this
https://github.com/hereisSwapnil/ai-council
Oh neat. Yeah, if something like that had existed (and I’d been aware of it) I probably would have used it instead of building my own shoestring version.