HuggingChat Launches ML Intern: Run Evals, Fine-Tune and Publish Spaces via Chat
pcuenq · x · 2026-09-09
Hugging Face has introduced a new HuggingChat feature called "ML Intern." Once enabled, the chat assistant taps into the entire HF ecosystem: you can make requests directly in conversation—such as running an evaluation, finding datasets, doing fine-tuning, or reproducing a paper—and it will research automatically, train with HF Jobs when needed, and even publish Spaces directly. The official positioning is "you don't need to be an ML expert to have ML ideas": start from a conversation and end up with a deployable product.
Related event: Hugging Face Launches ML Intern Conversational Agent in HuggingChat(3 posts)→
More from coding & agent
- Salesforce releases EvoHarnessBench to test agents against evolving tool harnesses — Salesforce · 2026-09-10
- Tsinghua + Qwen paper: rebuilding agent workspaces beats imitating trajectories, lifts Terminal-Bench to 58.1% — rohanpaul_ai · 2026-09-10
- Users urged to make Codex/Claude document their process before models become unavailable — moonsandhues · 2026-09-10
- Whatomate: open-source single-binary WhatsApp AI chatbot platform hits 1.5k GitHub stars — tom_doerr · 2026-09-10
- Dev replaces bloated AI chat with a Kanban board that agents read and update themselves — Clean-Vermicelli-700 · 2026-09-10
- Nomos: an open-source framework for testing whether AI agent permissions have grown too broad — Excellent-Hour7253 · 2026-09-10