---
format: "aidr-story-markdown/v1"
id: "bf08c7b0ac6a75f777cb915a239cd52f4eda2344fa9056462c3112d27e3bcc39"
canonical_url: "https://aidr.today/bf08c7b0?lang=en"
title: "If you don't run your own LLM proxy, how do you know whats going on?"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-18T21:09:12.000Z"
category: "Infra"
topics: ["llm"]
source_urls: ["https://jrdsgl.com/if-you-dont-run-your-own-llm-proxy-how-the-fuck-do-you-even-know-whats-going-on/","https://news.ycombinator.com/item?id=50145507"]
summary: "The article argues that running your own LLM proxy is necessary to understand what is happening with your AI workloads."
---

# If you don't run your own LLM proxy, how do you know whats going on?

> [Open the canonical story](<https://aidr.today/bf08c7b0?lang=en>)

**Published:** 2026-10-18T21:09:12.000Z
**Category:** Infra
**Topics:** llm

## Summary

The article argues that running your own LLM proxy is necessary to understand what is happening with your AI workloads\.

## Sources

- [Story source](<https://jrdsgl.com/if-you-dont-run-your-own-llm-proxy-how-the-fuck-do-you-even-know-whats-going-on/>)
- [Discussion](<https://news.ycombinator.com/item?id=50145507>)