Simon Willison has updated his llm-echo debug plugin to better simulate token usage for LLM releases. The latest version, 0.5, now accounts for tool calls, system prompts, and reasoning tokens in its usage counts. This enhancement allows developers to more accurately track token consumption during testing, as demonstrated by an example showing input and output token calculations. AI
IMPACT Enhances LLM development tooling by providing more accurate token usage simulation for testing.
RANK_REASON The item describes an update to a specific debugging tool for LLMs, not a core AI release or significant industry event.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →