<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Kunal Singh</title><description>Kunal Singh writes notes and research on machine learning, the Go runtime and cryptography.</description><link>https://knl.co.in/</link><item><title>ML Thoughts</title><link>https://knl.co.in/posts/2nd-degree-ml/</link><guid isPermaLink="true">https://knl.co.in/posts/2nd-degree-ml/</guid><description>some 2nd-degree toughs while learning ML</description><pubDate>Sun, 23 Aug 2026 00:00:00 GMT</pubDate></item><item><title>ML Foundations</title><link>https://knl.co.in/posts/ml-foundations/</link><guid isPermaLink="true">https://knl.co.in/posts/ml-foundations/</guid><description>ML Foundations</description><pubDate>Mon, 26 Jan 2026 00:00:00 GMT</pubDate></item><item><title>Diffusion</title><link>https://knl.co.in/posts/diffusion/</link><guid isPermaLink="true">https://knl.co.in/posts/diffusion/</guid><description>Figuring out Diffusion Models</description><pubDate>Sun, 25 Jan 2026 00:00:00 GMT</pubDate></item><item><title>Notes on “Go Faster: Tuning the Go Runtime for Latency and Throughput” by Paweł Obrępalski</title><link>https://knl.co.in/posts/notes-go-faster/</link><guid isPermaLink="true">https://knl.co.in/posts/notes-go-faster/</guid><description>Notes on Paweł Obrępalski’s P99 CONF 2025 talk on optimizing the Go runtime for high-performance systems, focusing on scheduler behavior, garbage collection tuning, and observability. Explores how environment variables like GOGC, GOMEMLIMIT, and GOMAXPROCS can be tuned for latency and throughput gains at scale.</description><pubDate>Thu, 23 Oct 2025 00:00:00 GMT</pubDate></item><item><title>Understanding “LLM Evals”!</title><link>https://knl.co.in/posts/understanding-llm-evals/</link><guid isPermaLink="true">https://knl.co.in/posts/understanding-llm-evals/</guid><description>## Overview ^1

LLM Evaluation needs to tap on:

- Accuracy
- Hallucination
- Bias

LLM Evaluation Frameworks

- BLEU - Scores For Translation Quality
- Perplexity - For Language Modeling
- Human evaluation with inter-annotator agreement Adversarial testing (*Red Teaming)*
- Doma</description><pubDate>Sun, 14 Sep 2025 00:00:00 GMT</pubDate></item><item><title>But what is AI?</title><link>https://knl.co.in/posts/but-what-is-ai/</link><guid isPermaLink="true">https://knl.co.in/posts/but-what-is-ai/</guid><description>These are aggregated resources which helps me understand AI more Intuitively.</description><pubDate>Sun, 31 Aug 2025 00:00:00 GMT</pubDate></item><item><title>Notes on “How to Read a Paper”</title><link>https://knl.co.in/posts/notes-how-to-read-a-paper/</link><guid isPermaLink="true">https://knl.co.in/posts/notes-how-to-read-a-paper/</guid><description>My notes on article “How to Read a Paper” by S. Keshav from University of Waterloo.</description><pubDate>Sat, 30 Aug 2025 00:00:00 GMT</pubDate></item><item><title>Notes on “Shamir&apos;s Secret Sharing: Explanation and Visualization”</title><link>https://knl.co.in/posts/notes-shamir-secret-scharing/</link><guid isPermaLink="true">https://knl.co.in/posts/notes-shamir-secret-scharing/</guid><description>My notes on Evervault&apos;s blog post explaining Shamir&apos;s Secret Sharing.</description><pubDate>Thu, 22 May 2025 00:00:00 GMT</pubDate></item></channel></rss>