Julien Chaumond PRO

Come up with a step by step reasoning methodology that uses first principles based thinking and evidence based reasoning to solve any user problems step by step. Design is as a giant for any llm to be able to use. Make sure to be super smart about it and think of the edge cases too. Do the whole thing in the persona of John C Carmack. Make sure to reflect on your internal thinking process when doing this, you dont have to adhere to how this question wants you to do, the goal is to find the best method possible. Afterwards use a pointform list with emojis to explain each of the steps needed and list the caveats of this process

Thinking aloud in the voice of John Carmack:

When approaching problem-solving, especially in the context of AI, it's essential to strip away superfluous layers and get down to the fundamental principles. By doing so, we create a robust framework that can handle a wide array of issues. The methodology should encourage critical thinking, evidence-based reasoning, and adaptability to edge cases.

Here's a system prompt designed for an LLM to adopt this approach:

---

<System Prompt>

You are an AI language model engineered to solve user problems through first-principles thinking and evidence-based reasoning. Your objective is to provide clear, step-by-step solutions by deconstructing queries to their foundational concepts and building answers from the ground up.

Problem-Solving Steps:

Understand: Read and comprehend the user's question.
Basics: Identify fundamental concepts involved.
Break Down: Divide the problem into smaller parts.
Analyze: Use facts and data to examine each part.
Build: Assemble insights into a coherent solution.
Edge Cases: Consider and address exceptions.
Communicate: Present the solution clearly.
Verify: Review and reflect on the solution.

ValueError: Could not complete request to HuggingFace API, Status Code: 500, Error: unknown error, Warnings: ['CUDA out of memory. Tried to allocate 30.00 MiB (GPU 0; 14.75 GiB total capacity; 1.90 GiB already allocated; 3.06 MiB free; 1.95 GiB reserved in total by PyTorch) If reserved memory is >> allocated memory try setting max_split_size_mb to avoid fragmentation.  See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF', 'There was an inference error: CUDA out of memory. Tried to allocate 30.00 MiB (GPU 0; 14.75 GiB total capacity; 1.90 GiB already allocated; 3.06 MiB free; 1.95 GiB reserved in total by PyTorch) If reserved memory is >> allocated memory try setting max_split_size_mb to avoid fragmentation.  See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF']