Exploring AI Learning, the specifics of Large Language Models, including architecture, prompt engineering, fine-tuning, RAG, and their application in text-based tasks.
Watch or Listen on YouTube Recursive Language Models: Introduction A funny thing happens when you give a modern LLM a huge context window. You expect it to feel like upgrading from a studio apartment to a warehouse. In practice, it often feels like moving into that warehouse and then forgetting what you put where. As … Read more
Watch or Listen on YouTube Deep Delta Learning Explained: Introduction ResNet’s big trick is almost insultingly simple. Add an identity shortcut, stop gradients from dying, train deeper models. The shortcut is a safety rail, and in deep residual learning for image recognition it turned “very deep” from a heroic gamble into a default option. That … Read more
Watch or Listen on YouTube The Great Swap: Trust in AI Science Introduction A funny thing happened after ChatGPT shipped. The average paper got easier to read. Not “more correct,” not “more insightful.” Just smoother. The kind of prose that used to signal a careful researcher suddenly became the default setting. That’s why the “AI … Read more
Watch or Listen on YouTube DeepSeek mHC Explained: Stable Hyper-Connections For Wider Transformers Introduction If you have ever watched a large run go sideways at 3 a.m., you know the weird part is not the failure. The weird part is how sudden it is. Loss looks fine, gradients look normal, then a small architectural “improvement” … Read more
Watch or Listen on YouTube TTT E2E: 128K Context Without the Full KV Cache Tax Introduction Long prompts feel like a superpower right up until you pay for them. You paste in 80K tokens of logs, code, or chat history, and the model spends the next few seconds doing what looks like “thinking,” but is … Read more
Watch or Listen on YouTube AI Accelerators: What They Are, How They Work, and Which Ones Matter in 2026 Introduction If you’ve ever watched your laptop’s fan spin up while a “simple” AI feature runs, you’ve met the real villain of modern computing: math at industrial scale. Neural networks don’t think in sentences. They think … Read more
Watch or Listen on YouTube Next Embedding Prediction (NEPA): Introduction A lot of self-supervised vision feels like an elaborate workaround. Two crops, three heads, four losses, and a decoder you throw away the moment you start fine-tuning. This paper tries something refreshingly blunt. It asks: what if we just did prediction, the way language models … Read more