Post

Whenever I read discourse on AI energy/water use that focuses on the "median query," I can't help but feel misled. Coding agents like Claude Code send hundreds of longer-than-median queries every session, and I run dozens of sessions a day. On my blog: www.simonpcouch.com/blog/2026-01...

Dr Vincent Raoult

@sawsharkman.bsky.social

20 Jan

They pick the median probably because it makes them look better. In this case it's probably better to use an average...

jake

@yetanotheruseless.com

21 Jan

Who's "picking" anything here? He's accurately saying he's a far outlier, using way more than typical, and showing how much that is.

Dr Vincent Raoult

@sawsharkman.bsky.social

21 Jan

I mean the discourse using the median. Mean is much more appropriate to discuss impacts like this because it includes rather than excludes far outliers.

jake

@yetanotheruseless.com

but it's a bit *too* sensitive to the outliers! Esp. in an environment where some few users might be like Mr Gas Town, running 12 Claude Code instances in parallel all day - their potential impacts are huge, but comparing to them might make the OP's usage seem small. Median's better, no?

21/1/26, 3:27 am0 reposts0 likes

Michael Warkentin

@michaelwarkentin.com

21 Jan

Since when do we need just one statistic to properly analyze something? Give us median, give us average, give us p75 and p99 and p100.