Coding

I ran npx -y ccusage monthly --compact to get the following break-up of my AI coding agent costs. Month Codex Claude 2025-09 $37.47 $2.29 2025-10 $106.79 $9.13 2025-11 $100.35 $14.24 2025-12 $240.69 $24.88 2026-01 $100.89 $20.28 2026-02 $323.21 $29.46 2026-03 $1996.32 $134.87 2026-04 $401.36 $47.07 2026-05 $378.20 $45.13 This shows the ROI of my $20 subscriptions to each. I get ~$35 worth of API calls for my $20 Claude Pro subscription and ~$400 of API calls for my $20 ChatGPT Plus subscription (on top of my ChatGPT chats.) ...

I’d love for Claude or ChatGPT to answer questions like: What meetings am I not setting up that I really should be? or: Based on my activities since 9 May 2026, what should I blog about? or: Who in my professional life most deserves an unreasonable gesture? From data. My files, emails, calendar, contacts, transcripts, blogs, notes, code, browsing history, logs, random Markdown files I forgot I wrote. Hence, a Local MCP. ...

I’m a man of simple needs. All I want is: when I’m on Google Meet, I turn on captions. I wanted to click a bookmarklet and save those captions into a local Markdown file. (So that an AI agent can guide me from it.) Hence, Google Meet Captions. The code is in gmeetcaptions/. Drag the button to your bookmarks bar. Join a Meet. Turn on captions. Click it. You get a tiny panel with two buttons: Copy and Start Recording. ...

Everyone needs a tracking URL shortener. Why tracking? I want to know if they opened my email and clicked the link. Why shortener? I want them to know what the link is about. For example, https://r.s-anand.net/edge-remote-debugging.html is so much more meaningful than https://chatgpt.com/share/68528565-0d34-800c-b9ec-6dccca01c24c I’ve used redirection services in the past - like t.co, bit.ly, goo.gl, ow.ly, and others. They tend to vanish, start charging, serve ads, etc. Here’s my solution: use static HTML for redirection. ...

Increasingly, I’m using Codex (or other AI coding agents) as the “operating system” to run programs. That is, rather than directly run programs, I have the coding agent run the program. Advantage: If the program breaks, or needs a configuration change, the coding agent debugs it and fixes it. I don’t need to do anything. This is particularly useful for installation. For example: Install demucs and run it against my music folder. ...

Terence Tao said, “We haven’t done many experiments … large-scale studies where we take a thousand problems and just test them.” So I told Claude: You know my style. Suggest some innovative experiments I could run. The first suggestion was cool! The Polya Audit. Polya’s How to Solve It lists 20 heuristics (work backwards, induction, analogy, etc.). Mathematicians treat these as wisdom. Nobody has ever measured which ones actually work, and on what problem types. ...

Based on several (i.e. two) recommendations, I subscribed to MiniMax. At $10/month, you get 1,500 requests every 5 hours and 15,000 every week. That’s a LOT! Using the same prompt I had Claude Code generate two data stories: The first paragraph, by Claude Sonnet 4.6 The first paragraph, by MiniMax M2.7 Here’s my comparison of the two. It’s partly based on Claude Opus 4.6’s comparison but I felt the same way. ...

Increasingly, I use coding agents instead of writing software. For example, I built a Blog UMAP. Then, I built Calvin UMAP. And more. But instead of building re-usable software, I just ran Claude with prior context. Increasingly, I use coding agents to run software. For example, I use Codex to classify my expense receipts. It writes re-usable code, but I run it using Codex, and it updates the code with new/edge cases. ...

I kept hearing that with the Nov 2025 release of Opus 4.5 and GPT 5.2 Codex, ex-coders were sprinting back to coding. On a sample of ~1,700 developers on GitHub, exactly ten fit the “dormant returner” profile. Here are a couple of examples: But they’re the exception. I could find only TEN out of 1,700 developers who returned. I also found a few who exited: To be fair, the vibe coding revolution is real, but maybe we are (I am) mis-interpreting it. ...

Similar to the embedding map of my blog posts, I created an embedding map of Calvin & Hobbes. It uses the same process as before. Video

I was at a panel on AI in SDLC at PyConf. Here’s the summary of my advice: Process Make AI your entire SDLC loop. Record client calls, feed them to a coding agent to directly build & deploy the solution. Record your prompts, run post-mortems, and distill them into SKILLS.md files for reuse. Prompting Ask AI to make output more reviewable. Don’t waste time reviewing unclear output. Prefer directional feedback (feeling, emotion, intent) over implementational. Also give AI freedom to do things its way. Learn from that - you’ll be surprised. Learning ...

I created an embedding map of my blog posts. Each point is a blog post. Similar posts are closer to each other. They’re colored by category. I’ve been blogging since 1999 and over time, my posts have evolved. 1999-2005: mostly links. I started by link-blogging 2005-2007: mostly quizzes, how I do things, Excel tips, etc. 2008-2014: mostly coding, how I do things and business realities 2015-2019: mostly nothing 2019-2023: mostly LinkedIn with some data and how I do things 2024-2026: mostly LLMs … and this transition is entirely visible in the embedding space. ...

I run AI coding agents inside a Docker container for safety. The setup is dev.dockerfile: builds the image dev.sh: launches the container with the right mounts and env vars dev.test.sh: verifies everything works. I wrote them semi-manually and it had bugs. I had GitHub Copilot + GPT-5.4 High update tests and actually run the commands to verify the setup. Here’s what I learned from the process. 1. Make it easier to review. The first run took long. I pressed Ctrl+C, told Copilot to “add colored output, timing, and a live status line”. Then I re-ran. Instead of a bunch of ERROR: lines, I now got a color-coded output with timing + a live status line showing what’s running. ...

Since WEBM compresses videos very efficiently, I’ve started using videos more often. For example, in Prototyping the prototypes and in Using game-playing agents to teach. I use a fish script to compress screencasts like this: # Increase quality with lower crf= (55 is default, 45 is better/larger) # and higher fps= (5 is default, 10 is better/larger). screencastcompress --crf 45 --fps 10 a.webm b.webm ... To record the screencasts, I prefer slightly automated approaches for ease and quality. ...

It’s impressive how easy it is to find leaked API keys in public repositories. I asked Codex to run trufflehog on ~5,000 student GitHub accounts and (so far, after a few hours, 15% coverage), it found quite a few. Some are intended to be public, like Google Custom Search Engine keys. 1 2 const GOOGLE_API_KEY = "AIza..."; const GOOGLE_CX = "211a..."; Some are Gemini API keys. 1 2 3 4 5 6 7 api_key1 = "AIza..." But what’s really impressive is, when I ran: ...

I recorded a short screen cast of a demo I built. It was ~900KB - way too large to publish as a thumbnail. So I asked ChatGPT: What’s the best equivalent of squoosh.app for WEBM compression? I’m looking for a free modern high-quality online video compressor. There are a few, and they compressed it to a third of its size, but 300KB is still too large. So I attached the original and asked: ...

One of my goals this year is to “Automate finance + tax”. Today, I took a baby step by organizing my expenses. This is my current process: STEP 1: Download PDF receipts (from OpenAI, Anthropic, Google, and other cloud/AI services) STEP 2: Organize them, so I know which receipt to upload against which expense STEP 3: Submit on SAP Concur. All steps are manual as of now. I automated STEP 2: Organize them. ...

Graded Assignment 1 (GA1) for the Tools in Data Science course is released and is due Sun 15 Feb 2026. See https://exam.sanand.workers.dev/tds-2026-01-ga1 If you already started, you might notice some questions have changed. Why is GA1 changing? Because some questions don’t work. For example: We replaced Claude Artifacts with a Vercel question because Claude won’t allow a proxy anymore. A question had unintentionally wrong instructions. (Some questions have intentionally wrong instructions, but those are, …um… intentional). Someone changed an API key. … etc. When will GA1 stabilize? Probably by end of day, Sun 9 Feb 2026? ...

This morning, I migrated my Tools in Data Science course page from Docsify to Hugo using Codex. Why? Because Docsify was great for a single term. For multiple terms, archives became complex. I still could have made it work, but it felt like time to move towards a static site generator. I don’t know how Hugo or Go work. I didn’t look at the code. I just gave Codex instructions and it did the rest. This gives me a bit more confidence that educators can start creating their own course sites without needing coding or platforms. Soon, they might not be stuck to LMSs either - they can build their own. ...

Gemini lets you copy individual responses as Markdown, but not an entire conversation. That’s useful if you want to save the chat for later, pass it to another LLM, or publish it. So I built a bookmarklet that scrapes the entire conversation as Markdown and copies it to the clipboard. SETUP: Drag the bookmarklet to your bookmarks bar. USAGE: On a Gemini chat page, click the bookmarklet. It copies the chat as Markdown. ...