<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Nikesh Gyawali</title><description>Personal website and blog of Nikesh Gyawali - Postdoctoral Fellow at Kansas State University working on large language models, NLP, and machine learning.</description><link>https://gnikesh.github.io/</link><language>en-us</language><item><title>Catan Board Generator: from weekend idea to working app with vibe coding</title><link>https://gnikesh.github.io/blog/catan-map-generator/</link><guid isPermaLink="true">https://gnikesh.github.io/blog/catan-map-generator/</guid><description>How a simple question while playing Catan - could I generate balanced boards automatically? - became a production-grade generator, built over a weekend using an AI vibe-coding workflow with Claude Code.</description><pubDate>Sun, 22 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Dockerized microservices backend: building software the way production teams ship it</title><link>https://gnikesh.github.io/blog/docker-notes-app/</link><guid isPermaLink="true">https://gnikesh.github.io/blog/docker-notes-app/</guid><description>A hands-on Dockerized backend platform with a production-ready microservices architecture - two independent Express/MongoDB services behind an Nginx reverse proxy, with clear service boundaries, isolated networks, and environment parity from development to deployment.</description><pubDate>Sun, 22 Feb 2026 00:00:00 GMT</pubDate></item><item><title>From Tweets to Takes: Training an AI to Read the Gun-Control Debate</title><link>https://gnikesh.github.io/blog/from-tweets-to-takes-training-an-ai-to-read-the-gun-control-debate/</link><guid isPermaLink="true">https://gnikesh.github.io/blog/from-tweets-to-takes-training-an-ai-to-read-the-gun-control-debate/</guid><description>We created GUNSTANCE, the first publicly available machine-learning dataset focused purely on the &quot;banning guns&quot; and &quot;regulating guns&quot; sides of the debate, plus a hybrid self-training + LLM method that reads brand-new conversations as they unfold.</description><pubDate>Mon, 19 May 2025 00:00:00 GMT</pubDate></item><item><title>Method of least squares</title><link>https://gnikesh.github.io/blog/method-of-least-squares/</link><guid isPermaLink="true">https://gnikesh.github.io/blog/method-of-least-squares/</guid><description>When there are more equations than unknowns, there is usually no exact solution. The method of least squares - introduced by Adrien-Marie Legendre in 1805 while studying the orbits of comets - tells us how to find the best solution by minimizing the total squared error.</description><pubDate>Fri, 25 Apr 2025 00:00:00 GMT</pubDate></item><item><title>GPU Monitoring app with Django</title><link>https://gnikesh.github.io/blog/gpu-monitoring-app-with-django/</link><guid isPermaLink="true">https://gnikesh.github.io/blog/gpu-monitoring-app-with-django/</guid><description>A tiny GPU monitoring web app built with Django and gpustat that shows real-time GPU usage, memory, and active processes per user - handy in shared research labs and clusters.</description><pubDate>Sun, 13 Apr 2025 00:00:00 GMT</pubDate></item><item><title>Importance of statistics in science &amp; hypothesis test</title><link>https://gnikesh.github.io/blog/importance-of-statistics-in-science-hypothesis-test/</link><guid isPermaLink="true">https://gnikesh.github.io/blog/importance-of-statistics-in-science-hypothesis-test/</guid><description>Statistics is the backbone of scientific research - from designing robust studies and sampling to hypothesis testing with p-values and significance levels. This article walks through the key elements of study design and the process of hypothesis testing.</description><pubDate>Wed, 09 Apr 2025 00:00:00 GMT</pubDate></item><item><title>Privacy-Preserving Deep Learning: How GANs and Differential Privacy Work Together</title><link>https://gnikesh.github.io/blog/privacy-preserving-deep-learning-how-gans-and-differential-privacy-work-together/</link><guid isPermaLink="true">https://gnikesh.github.io/blog/privacy-preserving-deep-learning-how-gans-and-differential-privacy-work-together/</guid><description>GANs can generate useful synthetic data, and differential privacy adds a mathematical guarantee that no individual leaks from the training set. Together they enable collaborative, privacy-preserving deep learning - here is how.</description><pubDate>Tue, 11 Jun 2024 00:00:00 GMT</pubDate></item><item><title>A blog post about Life</title><link>https://gnikesh.github.io/blog/a-blog-post-about-life/</link><guid isPermaLink="true">https://gnikesh.github.io/blog/a-blog-post-about-life/</guid><description>The entire blog post below was generated by GPT-3. I was learning about OpenAI transformer-based language models and was astonished by how powerful they are, so I decided to see if one could write a post for me.</description><pubDate>Mon, 25 Apr 2022 00:00:00 GMT</pubDate></item><item><title>My favorite 2021 books</title><link>https://gnikesh.github.io/blog/my-favorite-2021-books/</link><guid isPermaLink="true">https://gnikesh.github.io/blog/my-favorite-2021-books/</guid><description>I read a lot in 2021. Here are five books I really loved: Educated by Tara Westover, The Body by Bill Bryson, Think Again by Adam Grant, Sapiens by Yuval Noah Harari, and Deep Work by Cal Newport.</description><pubDate>Thu, 13 Jan 2022 00:00:00 GMT</pubDate></item><item><title>Book: &quot;The 5 AM Club&quot;</title><link>https://gnikesh.github.io/blog/book-the-5-am-club/</link><guid isPermaLink="true">https://gnikesh.github.io/blog/book-the-5-am-club/</guid><description>My takeaways from The 5 AM Club by Robin Sharma - an inspiring book that teaches the 20/20/20 rule for transforming your mornings, and my attempt to actually follow it.</description><pubDate>Fri, 05 Mar 2021 00:00:00 GMT</pubDate></item><item><title>Tail Recursive nth Fibonacci Number</title><link>https://gnikesh.github.io/blog/tail-recursive-nth-fibonacci-number/</link><guid isPermaLink="true">https://gnikesh.github.io/blog/tail-recursive-nth-fibonacci-number/</guid><description>How to compute the nth Fibonacci number efficiently using tail recursion in Standard ML and Python - reducing exponential time complexity to linear and stack space from linear to constant.</description><pubDate>Wed, 03 Mar 2021 00:00:00 GMT</pubDate></item><item><title>Maximum Subsequence Sum of an Array</title><link>https://gnikesh.github.io/blog/maximum-subsequence-sum-of-an-array/</link><guid isPermaLink="true">https://gnikesh.github.io/blog/maximum-subsequence-sum-of-an-array/</guid><description>Solving the maximum (contiguous) subsequence sum problem in Python from a slow brute-force O(n^3) approach down to an elegant linear-time algorithm that also returns the subsequence itself.</description><pubDate>Sun, 07 Feb 2021 00:00:00 GMT</pubDate></item><item><title>From &quot;I Can&apos;t Quit Vim&quot; to &quot;I Can&apos;t Live Without It&quot;</title><link>https://gnikesh.github.io/blog/from-i-cant-quit-vim-to-i-cant-live-without-it/</link><guid isPermaLink="true">https://gnikesh.github.io/blog/from-i-cant-quit-vim-to-i-cant-live-without-it/</guid><description>How I went from fearing Vim to making it my daily driver for a full year, plus a practical guide to the modes, the key commands, customization, and the gotchas that trip up every newcomer.</description><pubDate>Sun, 11 Aug 2019 00:00:00 GMT</pubDate></item></channel></rss>