Numerical precision
How many bits a computer uses to store each number; fewer bits mean faster sums but less exact results.
Also: FP64, FP32, FP16
Computers store decimal numbers in floating-point formats of a set size. Scientific simulation traditionally uses 64-bit (FP64) for accuracy. AI tolerates much less: training usually runs in 16-bit formats such as BF16, increasingly with 8-bit FP8 parts, and inference may go down to 4 bits. Each halving of the bits roughly doubles the speed of the arithmetic and halves the memory per value. This is why a chip's AI performance can be many times its FP64 figure, and why comparisons must name the precision.