| ▲ | pvillano 3 hours ago | |
Yes, but a 10x larger model is only marginally better, and 10x cheaper training runs is only useful if you can find a use for 10x as many. | ||
| ▲ | aaronblohowiak 2 hours ago | parent [-] | |
more experiments. | ||
| ▲ | pvillano 3 hours ago | |
Yes, but a 10x larger model is only marginally better, and 10x cheaper training runs is only useful if you can find a use for 10x as many. | ||
| ▲ | aaronblohowiak 2 hours ago | parent [-] | |
more experiments. | ||