DeepLearning.AI course teaches agents to call TabPFN tabular foundation models
leslysandra · x · 2026-11-19
DeepLearning.AI and Prior Labs launched a short course, "Tabular Foundation Models for Data Science Agents," taught by Frank Hutter, Eliott Kalfon, and Tuana Çelik — about 1.5 hours with 8 video lessons, 4 code examples, and 2 graded assignments.
Key topics:
- How open-weight tabular foundation models like TabPFN predict on new datasets via in-context learning, without training a model from scratch
- Classification, regression, and forecasting, plus KV caching to speed up repeated predictions
- Frank Hutter walks through training your own nano TabPFN from scratch on synthetic data
- Most practical part: giving Claude Code the TabPFN MCP server and a skill, so the agent recognizes prediction tasks and calls the model as a tool
More from coding & agent
- Google Labs launches Stitch Loop, an agent that keeps improving shipped code — tokumin · 2026-11-19
- Speed up CI for AI-written code: caching, faster runners, test sharding — rseroter · 2026-11-19
- Netlify rebrands around agent-driven app building with live preview workflow — thisiskp_ · 2026-11-19
- Agentcard raises $8M to let agents buy from 5,000+ stores via Stripe Link — jeff_weinstein · 2026-11-19
- hstack open-sources one-command self-hosting for the Hermes agent — TheMoonMidas · 2026-11-19
- 16 AI models ran produce buying for 90 days — only 3 beat a simple reorder formula — ycombinator · 2026-11-19