aifollow.news
Back Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · Original publication time AI score40

Uber compacts engineers’ Claude Code sessions at 400,000 tokensMachine translation

AI introduction

Uber compacts engineers’ Claude Code sessions at 400,000 tokens, even on models with million-token context windows. Weekly agent requests grew 9.4-fold from February to August while overall AI spending stayed roughly flat since April; Uber gives no savings figure for this setting alone.

Original post · Original

The article text is unavailable in this language; an existing version is shown.

@rohanpaul_ai

https://t.co/1bqpVxUGj4

ReplyRohan Paul@rohanpaul_ai
Uber compacts engineers’ Claude Code sessions at 400K tokens, even on million-token models, after exhausting its AI budget. Weekly agent requests at Uber grew 9.4x from February to August and weekly active users of its AI coding tools grew 7x, yet overall AI spending has stayed roughly flat since April. With the model held constant, cost per 1,000 requests fell almost 34% from its peak and cost per session fell 52% from its June peak, but Uber gives no savings figure for any single default. Uber still runs MCP servers, but agents reach them through command-line tools tied to a central MCP gateway, because preloading descriptions for 100-plus tools costs 50K to 70K tokens before the first prompt.
View this post on X ↗

Source: Rohan Paul · x.com

Industry
Found an error? Send a correction