Running multiple LLMs sounds smart until you see the bill. We use them to...

https://medium.com/@gashomor/i-run-five-ai-models-in-one-chat-heres-what-multi-model-ai-actually-is-6a1bb329d292

Running multiple LLMs sounds smart until you see the bill. We use them to balance different strengths and failure modes, but mixing outputs can hide critical dissent. Be careful-aggregating models complicates privacy across providers.