A short YouTube commentary (by LARRUZ) describing the public release of a competitor's long system prompt (“secret sauce”) and why it matters for API users. The speaker highlights items in the prompt such as hallucination-prevention measures, human-interaction guidelines, and explicit references to model identities (e.g., 'Claude 3.5 sonnet').
ChatGPT's main competitor just released their secret sauce to why their product works so well in a blog post. This is their so called system prompt, and they're all publicly available now. And why is this interesting? And why can you use this? Well, I wasn't even aware of the fact that if you're using the API, you're forgoing these system prompts. You're not using all of these extra instructions and the context within this long system prompt. And there's a lot of good stuff in here. Hallucination prevention? Yes. Guidelines on how to interact with humans in a more productive manner. Absolutely. There's multiple instances of that self awareness of the fact that this model even exists and what the user means when he says Claude 3.5 sonnet that's in here too. And so much more.
