heatdrop.ai

Twenty-five bite-sized projects showing how to wire up LLMs, RAG, and agents into things that actually do work.

An HKUST professor bottled a decade of top-conference publishing and reviewing experience into structured AI prompts for grad students.

DataTalksClub's open course teaches RAG, agents, and vector search by making you ship a working AI assistant in 10 weeks.

A curated hub of notebooks, apps, and guides that treat Oracle AI Database as the single backbone for vectors, graphs, memory, and SQL.

Free PDF, Jupyter notebooks, and the stubborn insistence that you implement classic ML from scratch before touching PyTorch.

A notebook-based workout plan for PyTorch fluency, from linear regression up to building LLM components from scratch.

A living spreadsheet of which AI providers actually let you call their models for free, with rate limits and gotchas spelled out.

A living literature review that tracks whether researchers are using language models to attack, defend, or just benchmark each other.

Course materials for a paid bootcamp, open-sourced as notebooks, datasets, and a readable web book.

A curated index of 500+ data science resources that admits it's just a well-organized bookmark dump.

Chinese open-source community Datawhale built a from-zero embodied-AI course that gets you from `print('hello')` to fine-tuning SmolVLA and Pi0.

Curated tutorials, tool reviews, and monetization playbooks for coding with AI—written by one prolific developer and open to all.

Because "secure your LLM" is not a strategy.

Someone finally collected all the ML-for-security papers, datasets, and books in one place so you don't have to hunt through conference proceedings at 2 AM.

Curated technical deep-dives covering everything from NVLink signal integrity to Kubernetes GPU scheduling and Huawei NPU porting.

Someone finally collected all those "top projects" Medium posts into one giant table.

A GitHub repo that ranks and reviews third-party API gateways for Chinese developers who can't easily access OpenAI, Anthropic, or Google directly.

An open-source curriculum trying to replace ¥10,000 AI-agent training courses with runnable code, interview banks, and two shipped projects.

One popular creator's entire curriculum—learning paths, bug manuals, interview prep, and a 30-topic programming dictionary—packaged as a TypeScript site.

A curated ladder of Jupyter projects from Titanic survival to YOLOv8 pose estimation, each designed to be run immediately rather than read passively.