90% of the tokens your AI burns aren't from your code.

Every shell command your agent runs returns raw output.

`git status`, `find`, and `ls` are all read by the LLM in every single run.

A single `playwright test` run dumped enough output to consume 8,100 tokens.

Two… pic.twitter.com/yX1u9lcBo2

— AlphaSignal AI (@AlphaSignalAI) 8 mai 2026

90% of the tokens your AI burns aren't from your code. Every shell command your agent runs returns raw output. `git status`, `find`, and `ls` are all read by the LLM in every single run. A single `playwright test` run dumped enough output to consume 8,100 tokens. Two

→ View original post on X — @alphasignalai