cb98090f95cae2797e29e4b9372cd18bc143765d
tested on sample size of 100 bills matching the distribution of our data Compression saves ~11.5% on prompt tokens; completion/reasoning are roughly equal across the two sets. prompt completion reasoning total compressed 349,460 157,110 112,128 506,570 uncompressed 394,948 154,710 110,080 549,658 delta −45,488 +2,400 +2,048 −43,088
Languages
Python
70.9%
Nix
20.6%
HTML
7%
CSS
0.8%
Shell
0.5%
Other
0.1%