radelbamor

Screen-recorded mini eval of the Noeum-1-Nano (0.6B) AI/LLM on 28 random questions from a 10,000 youtu.be/MWOPkMqeBys?si… via @YouTube

Inspired by @karpathy, we built the LLMification engine. Static Math books → Dynamic LLM Data Worked problems >SFT Practice problems >RL environments Infinite, verified variations SymPy verification Algebra to Olympic-level math Micro-step process supervision and much more ..

What efficient AI looks like when you start from first principles. youtube.com/watch?v=Nu1mLW… model & weights on Hugging Face.

@karpathy Inspired by this post! I have this running now: PDF → Markdown → Infinite Generator → Code Execution Env. It's evolved into a full engine at this point. Sharing the code in the next few days.for math it's working fine, but physics is another story. Complexity increases 100x

Transforming human knowledge, sensors and actuators from human-first and human-legible to LLM-first and LLM-legible is a beautiful space with so much potential and so much can be done... One example I'm obsessed with recently - for every textbook pdf/epub, there is a perfect "LLMification" of it intended not for human but for an LLM (though it is a non-trivial transformation that would need human in the loop involvement). - All of the exposition is extracted into a markdown document, including all latex, styling (bold/italic), tables, lists, etc. All of the figures are extracted as images. - All worked problems get extracted into SFT examples. Any referenced made to previous figures/tables/etc. are parsed and included. - All practice problems are extracted into environment examples for RL. The correct answers are located in the answer key and attached. Any additional information is added as "answer key" for a potential LLM judge. - Synthetic data expansion. For every specific problem, you can create an infinite problem generator, which emits problems of that type. For example, if a problem is "What is the angle between the hour and minute hands at 9am?" , you can imagine generalizing that to any arbitrary time and calculating answers using Python code, and possibly generating synthetic variations of the prompt text. - All of the data above could be nicely indexed and embedded into a RAG database for later reference, or maybe MCP servers that make it available. Then just as a (human) student could take a high school physics course, an LLM could take it in the exact same way. This would be a significantly richer source of legible, workable information for an LLM than just something like pdf-to-text (current prevailing practice), which simply asks the LLM to predict the textbook content top to bottom token by token (umm - lame). As just a quick and crappy example of synthetic variations of the above example, GPT-5 gave me this problem generator (see image), which can now generalize that problem template to many variations: - When the time is 11:07 a.m., what is the degree measure of the angle between the hands? (Answer: 68) - Determine the angle in degrees between the clock’s hands at 4:14 a.m.. (Answer: 43) - What angle do the clock hands form when the time reads 11:47 a.m.? (Answer: 71) - At 7:02 a.m., what angle separates the hour hand and the minute hand? (Answer: 161) - At 4:14 a.m., calculate the angle made between the two hands. (Answer: 43) - What angle is formed by the hands of a clock at 4:45 p.m.? (Answer: 127) - What is the angle between the hour and minute hands at 8:37 p.m.? (Answer: 36) (infinite practice problems can be created...)

Noeum-1-Nano is live Competitive AI model trained on just 18B tokens (vs 2-12T standard) - 20-667× more data-efficient - Matches major lab nano models - Built entirely from scratch - Solo research from Vienna Model: huggingface.co/noeum/noeum-1-… #AI #EfficientAI #SovereignAI