Should we build LLMs like they're all-knowing experts of everything from programming languages to even neuroscience.<p>Is that really the right way to look at them? Or should it be made in such a way that they're so good at thinking, planning, and reasoning, with the unique capacity to learn and adapt incredibly fast - much like a fresh human brain?
What makes you think you have a choice? That's like asking whether binary heaps should be more ambitious or more polite.<p>Most of what you're describing is either faked by something outside the LLM, or if invented later will involve some completely new approach that will have a different name.<p>If you're thinking of prompts like "be friendly", that's not imbuing a behavior into the LLM itself, but rather adding a prefix to the document in the hopes it will have a desirable effect on what gets appended.