Uber blew through its AI budget, then dialed back context and reasoning in its AI coding tools

Posted

When an Uber engineer opens Claude Code for an interactive coding session, automatic compaction kicks in at 400,000 tokens, even for models with million-token context windows. Reasoning effort defaults to medium, not high. No MCP tool definitions load into the context at startup. The engineer didn’t pick any of those settings; Uber picked them.

Read more



Continue reading at VentureBeat »

Infrastructure