← Back to context Comment by inigyou 2 days ago All machine learning is benchmaxxing. It's a big problem. 1 comment inigyou Reply Sabinus 1 day ago It all comes down to how aligned the benchmarks are with what you want the model to do. If it's close, good performance. If it's not, unpredictable performance.
Sabinus 1 day ago It all comes down to how aligned the benchmarks are with what you want the model to do. If it's close, good performance. If it's not, unpredictable performance.
It all comes down to how aligned the benchmarks are with what you want the model to do. If it's close, good performance. If it's not, unpredictable performance.