#434 – Aravind Srinivas: Perplexity CEO on Future of AI, Search & the Internet

5148.093 - 5176.038 Aravind Srinivas

Isn't that weird? It's not that weird that such tricks really help a small model compared to a larger model, which might be even better instruction tuned and more common sense. So these tricks matter less for the, let's say GPT-4 compared to 3.5. But the key insight is that there's always going to be prompts or tasks that your current model is not going to be good at. And how do you make it