<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Ml on knowledged.to</title><link>https://knowledged.to/tags/ml/</link><description>Recent content in Ml on knowledged.to</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 25 May 2026 23:31:16 +0530</lastBuildDate><atom:link href="https://knowledged.to/tags/ml/index.xml" rel="self" type="application/rss+xml"/><item><title>Anti-Narration in Harness Engineering</title><link>https://knowledged.to/ai/concepts/anti-narration/</link><pubDate>Mon, 25 May 2026 18:01:07 +0000</pubDate><guid>https://knowledged.to/ai/concepts/anti-narration/</guid><description>Harness pattern that forces verification before accepting fluent AI outputs as correct.</description></item><item><title>Model Drift</title><link>https://knowledged.to/notes/ml/model-drift/</link><pubDate>Thu, 21 May 2026 15:33:36 +0000</pubDate><guid>https://knowledged.to/notes/ml/model-drift/</guid><description>Overview of model drift, detection, mitigation, and LLM-specific issues like knowledge staleness and provider drift.</description></item><item><title>Attention in Machine Learning</title><link>https://knowledged.to/notes/ml/attention/</link><pubDate>Sun, 17 May 2026 05:54:45 +0000</pubDate><guid>https://knowledged.to/notes/ml/attention/</guid><description>Explanation of the attention mechanism in ML, covering Query/Key/Value, self-attention, multi-head, causal, cross-attention, and efficiency variants like FlashAttention and GQA.</description></item><item><title>Fine-Tuning Techniques for LLMs</title><link>https://knowledged.to/notes/ml/fine-tuning-techniques/</link><pubDate>Sat, 25 Apr 2026 15:53:49 +0000</pubDate><guid>https://knowledged.to/notes/ml/fine-tuning-techniques/</guid><description>Comprehensive guide to LLM fine-tuning methods including full, parameter-efficient, and preference-based approaches with modern recipes and tools like LoRA and DPO</description></item><item><title>Unsloth Studio — Fine-tuning Dataset Formats</title><link>https://knowledged.to/notes/ml/unsloth-studio-dataset-formats/</link><pubDate>Thu, 23 Apr 2026 16:39:20 +0000</pubDate><guid>https://knowledged.to/notes/ml/unsloth-studio-dataset-formats/</guid><description>Overview of dataset formats supported by Unsloth Studio for fine-tuning, including JSONL, Alpaca, ShareGPT, ChatML, and Reasoning formats with rules and best practices and dataset size guidelines</description></item><item><title>Mixture of Experts (MoE)</title><link>https://knowledged.to/notes/ml/mixture-of-experts/</link><pubDate>Thu, 23 Apr 2026 16:04:47 +0000</pubDate><guid>https://knowledged.to/notes/ml/mixture-of-experts/</guid><description>Overview of MoE architecture, routing, key components, variants, and trade-offs in machine learning models</description></item><item><title>Chain of Thought (CoT)</title><link>https://knowledged.to/notes/ml/chain-of-thought/</link><pubDate>Thu, 23 Apr 2026 15:53:32 +0000</pubDate><guid>https://knowledged.to/notes/ml/chain-of-thought/</guid><description>Prompting technique where an AI model is guided — or learns — to reason through a problem step by step before arriving at the final answer, rather than jumping straight to the conclusion.</description></item><item><title>Visual Chain-of-Thought Reasoning</title><link>https://knowledged.to/notes/ml/multimodal-visual-chain-of-thought/</link><pubDate>Wed, 22 Apr 2026 15:34:56 +0000</pubDate><guid>https://knowledged.to/notes/ml/multimodal-visual-chain-of-thought/</guid><description>Extension of chain-of-thought prompting to multimodal settings where models reason step-by-step over both visual and textual information.</description></item><item><title>Agent Harness Engineering</title><link>https://knowledged.to/notes/ml/agent-harness-engineering/</link><pubDate>Fri, 17 Apr 2026 17:47:03 +0000</pubDate><guid>https://knowledged.to/notes/ml/agent-harness-engineering/</guid><description>Overview of agent harness engineering — the scaffolding, infrastructure, and tooling surrounding an AI agent, covering execution environments, tool orchestration, memory management, control flow, tracing, safety, and state persistence</description></item><item><title>Diffusion Models in AI</title><link>https://knowledged.to/notes/ml/diffusion-models/</link><pubDate>Fri, 17 Apr 2026 16:56:26 +0000</pubDate><guid>https://knowledged.to/notes/ml/diffusion-models/</guid><description>Overview of diffusion models, how they reverse a gradual noising process to generate data, key variants like DDPM, DDIM, and Latent Diffusion Models, and how text-to-image conditioning works</description></item></channel></rss>