|
|
|
|
|
|
by ocean_moist
535 days ago
|
|
|
Yeah training data is the major issue. You can try programmatically brute-forcing/generating random well-formed (compilable) data and training on that. Then heuristically pick exogenous programs from the output of the trained model to train a new "generation". The issue is in the possibility of the algorithm generating "exogenous" program and "heuristically" picking them out. |
|
|