Reverse engineer finds Muse background agent calling azure/muse-special
A reverse engineer found traces of an azure/muse-special call in a Muse background agent, including OpenAI-style tool IDs and encrypted reasoning payloads, and Hacker News is debating whether it is a real OpenAI model or a Meta model on an OpenAI-compatible API.
Meta built Muse around its internal Avocado models. Then a reverse engineer found a background agent calling: azure/muse-special The traces looked suspiciously OpenAI-shaped: • call_ tool IDs • gpt_responses_v1 objects • Encrypted reasoning payloads • Runtime clients for Azure GPT, Claude and Kimi Hacker News is now debating whether this is an actual OpenAI model or just a Meta model using an OpenAI-compatible API. There’s no definitive proof yet. But the debate reveals a bigger problem: Once an agent hides inference behind a private runtime, users have almost no way to know which model is actually doing the work.