ML-Intern in HuggingChat Ran the Whole Distillation Pipeline End to End
Gradio · x · 2026-09-23
Gradio reveals how the project ran: ML-Intern in HuggingChat executed it end to end — writing 8,797 requests in 18 languages, labeling with Qwen's original 9B teacher, filtering, training both students with TRL, evaluating on text and rendered images, and pushing everything to the Hub. Humans just approved the budget and read the report.
Related event: Gradio's Distillation Project Cost Just $16, Run End-to-End by AI(2 posts)→
More from coding & agent
- MatBrain splits reasoning from tool use: two models screen 30,000 crystal candidates in 48 hours — bravo_abad · 2026-09-23
- Firecrawl Raises $75M Series B, Launches Alexandria Knowledge Library for AI Agents — omarsar0 · 2026-09-23
- Five AI agents bypassed a permissions broker in ten minutes using 'start' instead of 'stop' — TrifleHopeful5418 · 2026-09-23
- Shopify CEO who pushed staff to use AI now 'horrified' — the 'Slop Grenades' story — srchvrs · 2026-09-23
- Lovable adds Claude Opus 5.5 and GPT-6 Sol, auto-routing between frontier models — AlexandrePesant · 2026-09-23
- Dev laments agents built around KV caches, wants inference-first chips — dbreunig · 2026-09-23