Hugging Face's new ML Intern lets anyone run machine learning experiments through a simple chat

The Decoder 9 Sep 2026, 10:38 UTC 1 min read

In brief

On September 9, 2026, Hugging Face introduced ML Intern, a chatbot-based assistant that turns plain-language ideas into machine learning experiments. It identifies suitable resources, forecasts computing costs, and can manage the approved workflow without exceeding the agreed budget.

ML Intern searches the Hugging Face Hub, GitHub, and the web for models, datasets, and tools.

After budget approval, it can prepare datasets, train and monitor models, publish results to the Hub, produce reports, and create demos.

Every training job receives a dashboard for progress tracking.

In a Hugging Face demonstration, one experiment ran for about six hours and cost less than $0.50.

Why it matters: The tool could make small-scale machine learning development more accessible while Hugging Face moves toward its acquisition by Nvidia and maintains its stated commitment to an open, hardware-neutral platform.

Editorial brief by Sakhanda Wire AI, based on reporting by The Decoder.

Hugging Face's new ML Intern lets anyone run machine learning experiments through a simple chat

Jonathan Kemper View the LinkedIn Profile of Jonathan Kemper

Sep 9, 2026

Hugging Face launched "ML Intern," an AI assistant built into its chatbot that lets users run machine learning experiments without any ML expertise. Users start by describing their idea in a conversation. The assistant then searches the Hugging Face Hub, GitHub, and the web to find the right models, datasets, and tools. Before kicking anything off, ML Intern estimates the required compute costs and suggests a budget. Once approved, it won't exceed that limit.

From there, the system works on its own. It can create datasets, train models, monitor running jobs, upload results to the Hub, write reports, and build demos. Each training run gets its own dashboard for tracking progress. One example from the demo video ran for about six hours and cost less than $0.50, according to Hugging Face.

The tool lowers the barrier for new ML projects on the platform. Meanwhile, Hugging Face itself is in the middle of an acquisition by Nvidia. CEO Jensen Huang has promised to keep the platform open and hardware-neutral.

AI News Without the Hype – Curated by Humans

Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.

Source: Gradio / LinkedIn

Hugging Face's new ML Intern lets anyone run machine learning experiments through a simple chat

AI News Without the Hype – Curated by Humans

More stories