Tag
The author measured token waste in AI coding agents and found 42% avoidable, then built a tool to catch it. The tool works with Claude Code, Cursor, and Codex.
Discusses token waste in AI agent workflows due to repeated context, introduces an open-source proxy called Badgr-auto for deduplication, and asks the community how they handle the issue.
A tweet criticizes how AI models waste tokens on HTML <div> tags, suggesting that tokenizers inefficiently allocate 40% of tokens to structural elements.
Teams scaling OpenAI usage face challenges in understanding cost drivers per feature, team, and customer, often relying on manual logging or tools like Finout for cost allocation and anomaly detection.