Anuranjan Yadav·Jul 12I Fine-Tuned a 1.5B Model to Solve Grade 6 Math Olympiad ProblemsFrom synthetic data to a working demo — a complete, beginner-friendly fine-tuning pipeline using Unsloth, LoRA, and a lot of Grade 6 maths.
Anuranjan Yadav·Mar 192.718: How This One Number Impacts What Your AI Says NextHave you ever wondered how an AI model, like ChatGPT, always seems to find the perfect next word in a sentence? Or how it knows to be more…
Anuranjan Yadav·Feb 10Username Suggestion: Building a Semantic Username Suggestion EngineA follow-up to [“Bloom Filters: Fast UserID Existence Check”]
Anuranjan Yadav·Jan 9Bloom filters: Fast UserID existence check using bloom filtersModern systems routinely handle millions or even billions of user IDs. A seemingly simple question can become surprisingly expensive:
Anuranjan Yadav·Aug 17, 2025What’s the Middle, Anyway? 🤔Remember that moment in primary school when the teacher asked, “What’s the middle of the data?” and you were taught to add everything up…
Anuranjan Yadav·Jan 22, 2025Daylight Savings Time — Should US ditch DSTShould the US Ditch Daylight Saving Time?
Anuranjan Yadav·Apr 7, 2024Time — Interesting timesTime is a very interesting concept. In today’s times, with AI all around, time has become even more relevant. Any prediction is based on…