It’s static, yes, but the static price is orders of magnitude higher. It still involves loading the whole model into VRAM and performing matrix multiplication on trillions of numbers
To be fair, I wouldn’t include “loading the whole model into VRAM” as part of the cost, given they can just keep it in there between different requests, and it might be down to hundreds of billions or dozens of billions instead of trillions… but even after all improvements it should still be orders of magnitude more expensive than normal search, which just makes their decision even crazier
It’s static, yes, but the static price is orders of magnitude higher. It still involves loading the whole model into VRAM and performing matrix multiplication on trillions of numbers
To be fair, I wouldn’t include “loading the whole model into VRAM” as part of the cost, given they can just keep it in there between different requests, and it might be down to hundreds of billions or dozens of billions instead of trillions… but even after all improvements it should still be orders of magnitude more expensive than normal search, which just makes their decision even crazier