How does it "reason" though, I thought LLM just generated likely next words?
But my hunches/experience is that `proper prompting + nature of code being logical` really showcases the power of whatever statistical distribution and alignment occurs during generation. Further, there must be major upstream efforts of high-quality training data curation + creation, an advanced training tricks like using a LLM's strong ability in one task area to support the training of an area it is weak in.
My understanding is kinda fuzzy because I haven’t coded it up myself, but this was the takeaway I got from this explanation (starts at 36:21)