<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>notes.saurav.io</title><description>Small fixes, one-line configs, and the flag that finally worked. Short notes from Saurav Sharma&apos;s terminal.</description><link>https://notes.saurav.io/</link><item><title>Stop Whisper from appending repetition loops to local dictation</title><link>https://notes.saurav.io/whisper-repetition-loop-cleanup/</link><guid isPermaLink="true">https://notes.saurav.io/whisper-repetition-loop-cleanup/</guid><description>My local voice-to-text app sometimes pasted hundreds of repeated words. The fix was VAD-aware audio clipping plus a conservative text filter, not another language model.</description><pubDate>Wed, 02 Sep 2026 23:00:00 GMT</pubDate></item><item><title>Codex says your skill descriptions were shortened</title><link>https://notes.saurav.io/codex-skills-context-budget-warning/</link><guid isPermaLink="true">https://notes.saurav.io/codex-skills-context-budget-warning/</guid><description>Codex CLI warns that skill descriptions were shortened to fit the skills context budget. Here is what it costs you and how to get back under the limit.</description><pubDate>Tue, 01 Sep 2026 22:30:00 GMT</pubDate></item><item><title>Turn off GPU acceleration in the VS Code terminal</title><link>https://notes.saurav.io/vscode-terminal-gpu-acceleration-off/</link><guid isPermaLink="true">https://notes.saurav.io/vscode-terminal-gpu-acceleration-off/</guid><description>The integrated terminal renders ghost characters, blank rows, or a smeared cursor. One setting fixes it.</description><pubDate>Tue, 01 Sep 2026 12:00:00 GMT</pubDate></item><item><title>The Claude Code Skills That Run My Content Pipeline</title><link>https://notes.saurav.io/claude-code-content-pipeline/</link><guid isPermaLink="true">https://notes.saurav.io/claude-code-content-pipeline/</guid><description>People ask how one person keeps a channel moving, so I made a video walking through my whole setup. Here is the gist. The boring parts stopped being manual. They became custom skills inside a seven-stage Claude Code pipeline that runs from my terminal: Strategy, Ideate, Produce,</description><pubDate>Thu, 23 Jul 2026 12:00:00 GMT</pubDate></item><item><title>OpenAI&apos;s /goal Command Lets Codex Agents Code for Days</title><link>https://notes.saurav.io/codex-goal-command-days-long-runs/</link><guid isPermaLink="true">https://notes.saurav.io/codex-goal-command-days-long-runs/</guid><description>OpenAI shipped `/goal` in the Codex CLI and the Codex app, so I made a video showing what it does and how to turn it on, since that is the question I kept seeing in every thread. The pitch: set a task, walk away, come back hours later to find it done, no babysitting the agent eve</description><pubDate>Thu, 23 Jul 2026 12:00:00 GMT</pubDate></item><item><title>The Codex Reset Feature Most People Missed</title><link>https://notes.saurav.io/codex-token-limit-reset/</link><guid isPermaLink="true">https://notes.saurav.io/codex-token-limit-reset/</guid><description>I hit my Codex weekly limit with three days still left in the week, which used to mean waiting it out. OpenAI added a way to reset the limit yourself, so I made a short video showing it live. Here are the exact steps if you would rather read them than watch. You no longer have to</description><pubDate>Thu, 23 Jul 2026 12:00:00 GMT</pubDate></item><item><title>Gemini CLI: The Free Claude Code Alternative</title><link>https://notes.saurav.io/gemini-cli-free-claude-code-alternative/</link><guid isPermaLink="true">https://notes.saurav.io/gemini-cli-free-claude-code-alternative/</guid><description>If you want Claude Code but do not want to burn API credits, Google made that easier. I made a video installing Gemini CLI from scratch and putting it through a real task, and here is the gist plus the steps so you can follow along without watching if you prefer. It is an open-so</description><pubDate>Thu, 23 Jul 2026 12:00:00 GMT</pubDate></item><item><title>What Generative AI Really Is (Without the Hype)</title><link>https://notes.saurav.io/generative-ai-explained-simply/</link><guid isPermaLink="true">https://notes.saurav.io/generative-ai-explained-simply/</guid><description>I set myself a small challenge: explain generative AI in about 90 seconds, no jargon, one analogy. The final cut runs about 81 seconds. Here&apos;s the idea behind it.</description><pubDate>Thu, 23 Jul 2026 12:00:00 GMT</pubDate></item><item><title>Run Kimi K3 in Hermes Agent: One API Key, One Config File</title><link>https://notes.saurav.io/kimi-k3-hermes-agent-openrouter-setup/</link><guid isPermaLink="true">https://notes.saurav.io/kimi-k3-hermes-agent-openrouter-setup/</guid><description>The Kimi K3 setup for Hermes Agent via OpenRouter is two files. Here is the walkthrough, the copy-paste configs, and the token-cost catch to test before you commit.</description><pubDate>Thu, 23 Jul 2026 12:00:00 GMT</pubDate></item><item><title>Mermaid + AI: Generate System Diagrams From Text in Seconds</title><link>https://notes.saurav.io/mermaid-ai-text-to-diagram/</link><guid isPermaLink="true">https://notes.saurav.io/mermaid-ai-text-to-diagram/</guid><description>I made a quick video on how I stopped drawing architecture diagrams by hand, and this post is the written version so you can copy the workflow straight off the page. I used to lose half an hour dragging boxes around in Lucidchart or Figma just to draw one diagram. Now I describe</description><pubDate>Thu, 23 Jul 2026 12:00:00 GMT</pubDate></item><item><title>One Codex Setting That Lets Ten Agents Work at Once</title><link>https://notes.saurav.io/parallel-agents-openai-codex/</link><guid isPermaLink="true">https://notes.saurav.io/parallel-agents-openai-codex/</guid><description>I made a quick video on a Codex setting most people never open, because flipping it on changed how I run bigger tasks. Multi-agent mode lets Codex run several agents at once, each with its own context window, reporting back to the main agent. In the video I turn it on and push it</description><pubDate>Thu, 23 Jul 2026 12:00:00 GMT</pubDate></item><item><title>How I Saved $84/Year on iCloud Storage Using Claude</title><link>https://notes.saurav.io/icloud-storage-cleanup-with-claude/</link><guid isPermaLink="true">https://notes.saurav.io/icloud-storage-cleanup-with-claude/</guid><description>Using Claude Code and Claude Web to analyze my iCloud folders, find bloat, and cut my monthly storage bill from $9.99 to $2.99.</description><pubDate>Wed, 21 Jan 2026 16:30:00 GMT</pubDate></item><item><title>From Score 79 to 94: How I Optimized My Static Blog for Speed</title><link>https://notes.saurav.io/optimizing-blog-performance/</link><guid isPermaLink="true">https://notes.saurav.io/optimizing-blog-performance/</guid><description>How I optimized my Hexo blog from a Lighthouse score of 79 to 94 by automating image compression (WebP), enabling lazy loading for images and scripts, and configuring proper cache headers.</description><pubDate>Sun, 28 Dec 2025 10:10:00 GMT</pubDate></item><item><title>How I Built This Blog: The Modern Serverless Tech Stack</title><link>https://notes.saurav.io/how-i-built-this-blog/</link><guid isPermaLink="true">https://notes.saurav.io/how-i-built-this-blog/</guid><description>A deep dive into the modern serverless tech stack (Hexo, AWS S3, CloudFront) and the AI-first workflow used to build and maintain this blog.</description><pubDate>Sun, 28 Dec 2025 00:35:00 GMT</pubDate></item><item><title>Consolidating Domains with CloudFront Functions</title><link>https://notes.saurav.io/consolidating-domains-cloudfront-functions/</link><guid isPermaLink="true">https://notes.saurav.io/consolidating-domains-cloudfront-functions/</guid><description>How I consolidated ai.saurav.io and cloud.saurav.io into a single domain using AWS CloudFront Functions for managing 301 redirects at the edge.</description><pubDate>Sat, 27 Dec 2025 21:35:00 GMT</pubDate></item><item><title>Cloud vs AI Hype: Why AI&apos;s Peak Is Higher</title><link>https://notes.saurav.io/ai-hype/</link><guid isPermaLink="true">https://notes.saurav.io/ai-hype/</guid><description>Comparing the peak hype cycles of Cloud Computing vs. AI: why AI&apos;s direct user impact and media speculation drive even higher public engagement.</description><pubDate>Fri, 27 Dec 2024 14:10:00 GMT</pubDate></item><item><title>UX is how AI apps differentiate themselves</title><link>https://notes.saurav.io/ai_ux/</link><guid isPermaLink="true">https://notes.saurav.io/ai_ux/</guid><description>Why User Experience (UX) is the key differentiator for AI applications, exploring how great design separates successful AI tools from the rest.</description><pubDate>Sun, 08 Dec 2024 14:10:00 GMT</pubDate></item><item><title>Humans in the Loop in the AI Era</title><link>https://notes.saurav.io/hitl/</link><guid isPermaLink="true">https://notes.saurav.io/hitl/</guid><description>Why Human-in-the-Loop (HITL) workflows are evolving from simple safety checks to strategic advantages in the era of sophisticated AI agents.</description><pubDate>Sat, 07 Dec 2024 14:10:00 GMT</pubDate></item><item><title>AI Agents: The Trillion-Agent Future Is Coming</title><link>https://notes.saurav.io/on-ai-agents/</link><guid isPermaLink="true">https://notes.saurav.io/on-ai-agents/</guid><description>A short reflection on the rise of LLM-based AI Agents and the prediction of a future populated by trillions of autonomous digital workers.</description><pubDate>Fri, 01 Dec 2023 23:28:38 GMT</pubDate></item><item><title>ChatGPT + Serverless Framework: Streamlining Cloud App Development</title><link>https://notes.saurav.io/serverless-plus-gpt/</link><guid isPermaLink="true">https://notes.saurav.io/serverless-plus-gpt/</guid><description>Streamlining Cloud App Development by combining ChatGPT&apos;s code generation with the Serverless Framework to instantly deploy a Python-based DynamoDB API.</description><pubDate>Fri, 11 Aug 2023 12:39:13 GMT</pubDate></item></channel></rss>