Step 1: Plan and design the LLM

1. Standard model design
2. LLM has the ability to re-train itself, to hit the re-train button. (no human required)
3. LLM is constantly re-working its training data to improve its training data. (no human required)

Note: focus on the LLM's ability to distinguish differences correctly, better from worse, yes from no and so on, successful compile vs errors, red from blue.

Demonstrator must be resource light enough for the LLM to perform these tasks.

Step 2: Eval Space

The tools that give the LLM the ability to test, proof and rework training data. For instance, a compiler.