Running multiple models seems smart until you look at the logs. Leveraging...

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

Running multiple models seems smart until you look at the logs. Leveraging different strengths and catching model-specific failure modes is useful for reliability. Just watch out for synthesis