Millisecond Converter

2026-04-24 · Source: Simon Willison's Weblog · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Fundamental Awareness, quick

Summary

Simon Willison has released a new online utility called Millisecond Converter, designed to simplify the conversion of millisecond durations into more human-readable units like seconds and minutes. This tool addresses a common inconvenience encountered when working with systems that report time in milliseconds, such as the LLM command-line utility for interacting with large language models. The LLM tool, developed by Willison, outputs prompt durations in milliseconds, making direct interpretation of performance metrics challenging without manual conversion. The Millisecond Converter provides a quick and efficient solution for developers and users to understand these time measurements more intuitively.

Key takeaway

For developers and users analyzing performance metrics from tools like LLM that report in milliseconds, you should integrate the Millisecond Converter into your workflow. This utility directly addresses the friction of manual time unit conversions, allowing you to quickly grasp prompt durations and other millisecond-based timings without mental arithmetic. Using this tool will streamline your analysis of system performance and response times.

Key insights

A new tool converts millisecond durations from LLM outputs into human-readable seconds and minutes.

In practice

• Convert LLM prompt durations to seconds/minutes.
• Simplify millisecond time interpretation.

Topics

• Millisecond Converter
• Large Language Models
• Time Conversion
• Developer Tools
• Prompt Duration

Best for: AI Engineer, Machine Learning Engineer, Prompt Engineer

Related on AIssential

• Why Your LLM App Works in Notebooks But Fails in Production — Decoupling long-running LLM API calls from the web server's request-response cycle prevents production failures.
• TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning — LLM agents struggle with multi-turn, decision-oriented time series analysis due to memory, uncertainty, and domain reasoning gaps.
• Automate Writing Your LLM Prompts — DSPy automates and optimizes LLM prompt creation and evaluation, ensuring robust, production-ready applications.
• How fast is 10 tokens per second really? — The HTML app visualizes LLM token output speeds from 5 to 800 tokens/second for practical understanding.
• Can someone buy Claude a clock? (Discussion in post) — Large Language Models lack inherent temporal awareness and require explicit context injection for accurate timekeeping.
• Why LLMs Get Math Wrong — Large Language Models (LLMs) often make mistakes in complex math problems and misinterpret tables because they process all input as flat text token sequences, treating math as patterns to predict rath…

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Simon Willison's Weblog.