Re:Autocomplete from Stack Overflow
by conjectures on Tuesday March 22, 2016 @12:02PM
(#11337501)
That actually sounds realistic. A well defined test suite is probably a good target for AI. Main issue is no partial wins, which are needed for training, so you'd need to break all functionality down into absolutely minimal units.
[ Parent
| on HN ]
Also if you overfit, your code is going to look like:
int add(int a, int b) {
if (a == 1 && b == 1) return 2;
if (a == -1 && b == 0) return -1;
if (a == 13 && b == 7) return 20;
return 0;
}
But at least it passes my unit test suite!Just rerun it with a lower target code complexity. You'll know you set it too low when it starts monkey-patching the test framework to avoid actually doing anything.
Re:Autocomplete from Stack Overflow
by Houshalter on Wednesday March 23, 2016 @03:29AM
(#11342697)
This can be avoided by optimizing for the simplest code that works. Checking many cases in multiple lines is always going to be longer and more complex than just a single operation on a single line.
Which is how AIs avoid overfitting, in general, by penalizing complexity.