|
|
|
|
|
by FloatArtifact
374 days ago
|
|
What I've always been confused on, why can't we train LLMs to code without ever seeing source code? If it understands human language enough, it should be able to understand the logic laid out in the documentation mapped to symbols to construct code. |
|
You can also describe your own app's syntax, architecture, function signatures, etc. in markdown files or just in chat and Cursor will write code that conforms to your desired syntax, which definitely doesn't exist in the training set.