|
|
|
|
|
|
by ramoz
1276 days ago
|
|
|
I'm no expert and don't have a proper answer. 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. |
|
|