Exploring AI Learning, the specifics of Large Language Models, including architecture, prompt engineering, fine-tuning, RAG, and their application in text-based tasks.
Introduction Some days in theoretical physics feel like mountain climbing. You spend hours inching upward through algebra, you finally reach a viewpoint, and the “beautiful simple formula” everyone promised turns out to be hiding behind a boulder labeled “one more identity.” Then there are days when a language model strolls by, points at your pile … Read more
Introduction Most “feature selection” stories start the same way. You have a model, you have a mountain of inputs, and you suspect half of them are doing more harm than good. Then you open a paper, see “NP-hard,” and quietly decide you will just throw everything into the network and let SGD sort it out. … Read more
Drifting Models: The One-Step Image Generator That Trains The “Diffusion Steps” Away Play Introduction Most generative models feel like they’re doing the same ritual: start with noise, take many tiny steps, hope you land on something beautiful before your GPU fan files for overtime. The paper Generative Modeling via Drifting (arXiv: 2602.04770v1) proposes a different … Read more
Codex App: Turn VS Code Into A Multi-Agent Command Center Play Introduction Coding used to be a lonely sport: editor on the left, terminal on the right, and your attention getting ping-ponged by bugs, reviews, and “quick” requests that aren’t quick. Now we have agents. The shock isn’t that they can write code, they can. … Read more
Self-Distillation Fine-Tuning (SDFT): The On-Policy Trick That Makes Continual Learning Finally Work Play Introduction Fine-tuning an LLM feels like doing surgery with oven mitts. You make one clean cut, the patient learns a shiny new skill, then you check the vitals and realize it forgot its own name. That is the default behavior of supervised … Read more
TTT-Discover Explained: Why Test-Time RL Outruns Best-of-N Sampling Play Introduction You have seen this movie. A model tackles a hard problem, fails, tries again, fails differently, then repeats the same mistake with fresh confidence. You can sample more. You can crank temperature. You can run best of n sampling until the GPU fans sound like … Read more
D4RT By DeepMind, Real-Time 4D Scene Reconstruction From One Video Play Introduction There’s a small magic trick your brain pulls off every time you watch a video. You do not just see pixels. You infer a world. You know what’s behind the mug when a hand passes in front of it. You keep track of … Read more