If you have such a test suite then you really don't need AI to write the code for you.
Writing a benchmark test is about 100x to 1000x easier than writing optimizations. A benchmark test can be as simple as:
func Benchmark(b *testing.B) { for range b.N { runCodeUnderBenchmark() } }
alt Hacker News
Writing a benchmark test is about 100x to 1000x easier than writing optimizations. A benchmark test can be as simple as:
Actually optimizing the runCodeUnderBenchmark() function is far more difficult.