I tested @huggingface ml-intern, given the prompt 'Fine-tune a Segment Anything Model (SAM) on a useful medical dataset. Train the model, an…

I tested @huggingface ml-intern, given the prompt "Fine-tune a Segment Anything Model (SAM) on a useful medical dataset. Train the model, and provide a comprehensive tutorial in a Jupyter Notebook file. Additionally, create a Hugging Face article/blog post documenting everything you have done." It did it all autonomously: - Researched via hf_papers & searched GitHub/HF Hub - Found an HF dataset & wrote the finetuning script - Trained it using HF compute (took ~1 hour) - Pushed the weights & wrote the article Here are the model weights, code, and the blog it generated: hf article https://huggingface.co/Mayank022/blog-fine-tuning-sam-medical-segmentation model weights https://huggingface.co/Mayank022/sam-vit-base-kvasir-polyp-segmentation Awesome stuff @akseljoonas , looking forward to use this. 🔥 Media Introducing ml-intern, the agent that just automated the post-training team @huggingface It's an open-source implementation of the real research loop that our ML researchers do every day. You give it a prompt, it researches papers, goes through citations, implements ideas in GPU …

I’ve been using ml-intern for a while, and it genuinely changed my workflow. It's super good at: - Model/Dataset discovery. - Post-Training …
Karpathy's autoresearch repo started an impressive trend. Agents can now train AI models to build SoTA agentic systems. And to think this is…
C++ CuTe / CUTLASS vs CuTeDSL (Python) in 2026 — what should new GPU kernel / LLM inference engineers actually learn?[D]

Source: Clem Delangue (X) | 2026-04-21

Related