Vibe Machine Learning with Hugging Face's ML Intern in HuggingChat
Melvin Vivas · X video post · 2026-09-15 · 0:36 · 356 views · Open on X
Topics: AI Dev Tools & Productivity, AI Agents, Tool Use & MCP, Programming & ML Foundations · Level: beginner
Summary
This is a short post with a silent video. It introduces ML Intern, which the quoted post calls a harness for AI building: it does for building ML/AI solutions what Claude Code and Cursor do for software development. ML Intern is now built into HuggingChat, so you describe an AI use case in plain language and the agent handles the work. Melvin Vivas calls this "Vibe Machine Learning" and says it's a good way to get started and to learn new things along the way.
Key points
- "Vibe Machine Learning" means describing an ML/AI goal in plain language and letting an agent build the solution, much like vibe coding.
- ML Intern is described as being to AI building what Claude Code and Cursor are to software development.
- The ML Intern harness is now fully built into HuggingChat (hf.co/chat).
- How it works: bring an AI use case and ask for it. The agent does the ML work.
- The creator recommends it as a beginner-friendly starting point and as a way to learn new ML techniques by watching what the agent does.
Resources mentioned
- HuggingChat · tool · hf.co · free
Hugging Face's chat interface for talking to AI models, which now includes the ML Intern agent harness. - ML Intern · tool · github.com · free
Hugging Face's agent harness that builds ML/AI solutions from plain-language requests.
Also in: ML Intern: Post-Train a Model by Chatting (Hugging Face) (Melvin Vivas on X · notes) - Claude Code · tool · code.claude.com · paid · recommended by both Bashiri Smith & Melvin Vivas
Build agents and pipelines from the terminal; the guide's main agentic coding tool.
Also in: First impressions: Claude Code in the cloud is good and fast (Melvin Vivas on X · notes), Why Claude Code feels faster: gzipped turns and instant cloud sessions (Melvin Vivas on X · notes), Watch What Fills Your Coding Agent's Context and When to Clear (Melvin Vivas on X · notes), Claude Code's Right Sidebar and Context Breakdown (Melvin Vivas on X · notes) and 124 more - Cursor · tool · x.com · free · recommended by both Bashiri Smith & Melvin Vivas
AI-native code editor (VS Code with AI built in).
Also in: Finding Cursor Cloud Agents After the Cursor–X Unification (Melvin Vivas on X · notes), Overnight notebook generation with Grok Bot, Cursor cloud and Grok 4.7 (Melvin Vivas on X · notes), Gemini 4 Argon in Cursor: CursorBench Score and Pricing (Melvin Vivas on X · notes), SpaceX AI / Cursor Ambassador Program Waitlist (Melvin Vivas on X · notes) and 135 more
Try this
- Open HuggingChat at hf.co/chat and use the ML Intern harness.
- Pick an AI use case and describe it to ML Intern in plain language.
- Look at the steps the agent takes so you learn new ML techniques from it.
More in AI Dev Tools & Productivity
- Docker image with coding agents pre-installed on a CUDA + PyTorch base
- jsonl-viewer: Live Traces for Codex Orchestrator and Subagents
- See live Codex traces with the jsonl-viewer tool
- T3Code: a better interface for terminal coding agents
- Bolt.new Adds Open Models (GLM, DeepSeek, Kimi) via Bolt Forge
- Quick Take: Cursor Projects Feature