Coding

Jaidev’s The Bridge of Asses reminded me of my first coding bridge. It was 1986. I’d completed class 6 and was in a summer coding camp at school. M Kothandaraman (“MK Sir”) was teaching us how to swap variables in BASIC on the BBC Micro. This code prints the first name in alphabetical order (“Alice”): 10 A = "Bob" 20 B = "Alice" 30 IF A > B THEN 40 TEMP = A 50 A = B 60 B = TEMP 70 END 80 PRINT A The homework was to print all details of the first alphabetical name: ...

Yesterday, I helped two people vibe-code solutions. Both were non-expert IT pros who can code but aren’t fluent. Person Alpha and I were on a call in the morning. Alpha needed to OCR PDF pages. I bragged, “Ten minutes. Let’s do it now!” But I was on a train with only my phone, so Alpha had to code. Vibe-coding was the only option. ...

Switching to a Linux machine has advantages. My thinking’s moving from apps to pipes. I wanted a spaced repetition app to remind me quotes from my notes. I began by writing a prompt for Claude Code: Write a program that I can run like uv run recall.py --files 10 --lines 200 --model gpt-4.1-mini [PATHS...] that suggests points from my notes to recall. It should --files 10: Pick the 10 latest files from the PATHs (defaulting to ~/Dropbox/notes) --lines 200: Take the top 200 lines (which usually have the latest information) --model gpt-4.1-mini: Pass it to this model and ask it to summarize points to recall ...

Jason Clarke’s Import AI 414 shares a Tech Tale about a game called “Go Think”: … we’d take turns asking questions and then we’d see how long the machine had to think for and whoever asked the question that took the longest won. I prompted Claude Code to write a library for this. (Cost: $2.30). (FYI, this takes 2.3 seconds in NodeJS and 4.2 seconds in Python. A clear gap for JSON parsing.) ...

I use Codex to write tools while I walk. Here are merged PRs: Add editable system prompt Standardize toast notifications Persist form fields Fix SVG handling in page2md Add Google Tasks exporter Add Markdown table to CSV tool Replace simple alerts with toasts Add CSV joiner tool Add SpeakMD tool This added technical debt. I spent four hours fixing the AI generated tests and code. What mistakes did it make? Inconsistency. It flips between execCommand("copy") and clipboard.writeText(). It wavers on timeouts (50 ms vs 100 ms). It doesn’t always run/fix test cases. Missed edge cases. I switched <div> to <form>. My earlier code didn’t have a type="button", so clicks reloaded the page. It missed that. It also left scripts as plain <script> instead of <script type="module"> which was required. Limited experimentation. My failed with a HTTP 404 because the common/ directory wasn’t served. I added console.logs to find this. Also, happy-dom won’t handle multiple exports instead of a single export { ... }. I wrote code to verify this. Coding agents didn’t run such experiments. What can we do about it? Three things could have helped me: ...

In the last few days, I’m coding with Jules (Google’s coding agent) while walking. Here are a few pull requests merged so far: Add features via an issue Write test cases Add docs Why bother? My commute used to be audiobook time. Great for ideas, useless for deliverables. With ChatGPT, Gemini, Claude.ai, etc. I was able to have them write code, but I still needed to run, test, and deploy. Jules (and tools like GitHub Copilot Coding Agent, OpenAI Codex, PR Agent, etc. which are not currently free for everyone) lets you chat clone a repo, write code in a new branch, test it, and push. I can deploy that with a click. ...

Earlier, I used Mermaid for technical architectures. But PlantUML seems a better option for cloud architecture diagrams. STEP 1: Copy the code Here’s a one-liner using files-to-prompt to copy all files in the current directory: fd | xargs uvx files-to-prompt --cxml | xclip -selection clipboard Or, you can specify individual files: uvx files-to-prompt --cxml README.md ... | xclip -selection clipboard STEP 2: Extract the cloud icons ...

I spoke about vibe coding at SETU School last week. Transcript: https://sanand0.github.io/talks/#/2025-05-10-vibe-coding/ Here are the top messages from the talk: What is vibe coding It’s where we ask the model to write & run code, don’t read the code, just inspect the behaviour. It’s a coder’s tactic, not a methodology. Use it when speed trumps certainty. Why it’s catching on Non-coders can now ship apps - no mental overhead of syntax or structure. Coders think at a higher level - stay in problem space, not bracket placement. Model capability keeps widening - the “vibe-able” slice grows every release. How to work with it day-to-day ...

I built podcast generator app in one-shot. I wrote a prompt, fed it to an LLM, and it generated the output without errors. I tested three LLMs, and all produced correct, working output. ChatGPT: o4-mini-high Functional but missed my specs in three ways: No error if I skip the API key No progress indicator for audio generation Both voices default to “ash” (should be “ash” and “nova”) Gemini 2.5 Pro: Works and looks great! Claude 3.7 Sonnet: Works great and looks even better! It still took me an hour to craft the prompt – even after I’d built a Python prototype and my colleague built a similar web version. ...

Here’s my current workflow to create technical architecture diagrams from code. STEP 1: Copy the code Here’s a one-liner using files-to-prompt to copy all files in the current directory: fd | xargs uvx files-to-prompt --cxml | xclip -selection clipboard Or, you can specify individual files: uvx files-to-prompt --cxml README.md ... | xclip -selection clipboard STEP 2: Prompt for the a Mermaid diagram Mermaid is a Markdown charting language. I use this prompt with O4-Mini-High or O3: ...

Here’s an LLM-generated podcast of what I coded last week. NotebookLM-inspired. The process proved straightforward. Get my GitHub commits for the week. Get the repositories I committed to for more context. Have an LLM generate a podcast script. I’m using GPT 4.1 Mini but might shift to Gemini 2.5 Flash or DeepSeek V3. …using a detailed prompt beginning with “You are a podcast script assistant for “Anand’s Weekly Codecast.” This episode is for the week of {WEEK}. …”. Here’s a sample output. Convert the script to audio. I’m using GPT 4o Mini TTS with customized voices of Ash and Nova. These now appear on my GitHub repo as a weekly summary. ...

What if you keep ask an LLM Improve the code - dramatically!? We used the new GPT 4.1 Nano, a fast, cheap, and capable model, to write code for simple tasks like “Draw a circle”. The we fed the output back and asked again, Improve the code - dramatically! Here are the results. Draw a circle rose from a fixed circle to a full tool: drag it around, tweak its size and hue, and hit “Reset” to start fresh. Animate shapes and patterns turned simple circles and squares into a swarm of colored polygons that spin, pulse, and link up by distance. Draw a fully functional analog clock grew from a bare face to one that builds all 60 tick marks in code—no manual copy‑paste needed. Create an interactive particle simulation went from plain white dots on black to hundreds of bright, color‑shifting balls that bounce, die, and come back to life. Generate a fractal changed from a single Mandelbrot image to an explorer you can zoom, drag, and reset with sliders and the mouse wheel. Generate a dashboard jumped from static charts to a live page with smooth card animations, modern fonts, and a real‑time stats box. A few observations. ...

I tried 2 experiments. Can I code a visual data story only using LLMs? Does this make me faster? How much? Has GitHub Copilot caught up with Cursor? How far behind is it? Can I recommend it? So I built a visual story for Lech Mazur’s elimination game benchmark (it’s like LLMs playing Survivor) using only the free GitHub Copilot as the AI code editor. SUMMARY: using LLMs and AI code editors make me a bit faster. It took me 7 hours instead of 10-12. But more importantly: ...

Here’s the GitHub Actions file (.github/workflows/deploy.yaml) I use to publish to GitHub pages. name: Deploy to GitHub Pages on: # Run when pushed. Use { branches: [main, master] } to run only on specific branches push: # Allow manual triggering of the workflow workflow_dispatch: # OPTIONAL: Run at a specific cron schedule, e.g. first day of every month at 12:00 UTC (noon) schedule: - cron: "0 12 1 * *" permissions: # To deploy to GitHub Pages pages: write # To verify that deployment originated from the right source id-token: write jobs: # Run as a single build + deploy job to reduce setup time deploy: # Specify the deployment environment. Displays the URL in the GitHub Actions UI environment: name: github-pages url: ${{ steps.deployment.outputs.page_url }} # Run on the latest Ubuntu LTS runs-on: ubuntu-latest \ steps: # Checkout the repository - uses: actions/checkout@v4 # Run whatever commands you want - run: echo '<h1>Hello World</h1>' > index.html # Upload a specific page to GitHub Pages. Defaults to _site - uses: actions/upload-pages-artifact@v3 with: path: . # Deploy the built site to GitHub Pages. The `id:` is required to show the URL in the GitHub Actions UI - id: deployment uses: actions/deploy-pages@v4 This is based on Simon Willison’s workflow and some of my earlier actions. ...

Fake data is usually boring if you analyze it. It’s usually uniform, with no outliers or interesting patterns. If I ask ChatGPT: Generate realistic fake tourism data using these columns: - Age - Nationality - Gender - Income - Booking_Channel - Month - Occupancy_Rate - Travel_Frequency - Spending Run the code and let me download the output as a CSV file. … the output is remarkably boring. Men & women from all countries and ages in every month visit equally. Income and spending are uniformly distributed - and the same pattern holds for all countries and ages. ...

At PyConf Hyderabad, I spoke about uv. It's a package manager for Python. I usually mix live demos into my narrative. So, rather than present with something static like PowerPoint (or Google Slides), I usually use: Front-end: Custom HTML mixed with RevealJS and CodePen. Observable is a good, too. Python: Jupyter Notebooks. Marimo is good, too. Others: Markdown and VS Code for most other things, e.g. SQL. For this talk, I needed to run commands on the shell. I evaluated: ...

Zohaib Rauf suggested using LLMs to spec code and using Cursor to build it. (via Simon Willison). I tried it. It’s promising, but my first attempt failed. I couldn’t generate a SPEC.md using LLMs At first, I started writing what I wanted. This application identifies the drugs, diseases, and symptoms, as well as the emotions from an audio recording of a patient call in a clinical trial. … and then went on to define the EXACT code structure I wanted. So I spent 20 minutes spec-ing our application structure and 20 minutes spec-ing our internal LLM Foundry APIs and 40 minutes detailing every step of how I wanted the app to look and interact. ...

In my Tools in Data Science course, I launched a Project: Automated Analysis. This is automatically evaluated by a Python script and LLMs. I gently encouraged students to hack this - to teach how to persuade LLMs. I did not expect that they’d hack the evaluation system itself. One student exfiltrated the API Keys for evaluation by setting up a Firebase account and sending the API keys from anyone who runs the script. ...

The Gemini documentation is clear: The File API service extracts image frames from videos at 1 frame per second (FPS) and audio at 1Kbps, single channel, adding timestamps every second. These rates are subject to change in the future for improvements in inference. Note: The details of fast action sequences may be lost at the 1 FPS frame sampling rate. Consider slowing down high-speed clips for improved inference quality. Individual frames are 258 tokens, and audio is 32 tokens per second. With metadata, each second of video becomes ~300 tokens, which means a 1M context window can fit slightly less than an hour of video. ...

It's surprisingly easy to clone a voice using F5-TTS: "A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching". Here's a clip of me, saying: I think Taylor Swift is the best singer. I've attended every one of her concerts and in fact, I've even proposed to her once. Don't tell anyone. (Which is ironic since I didn't know who she was until this year and I still haven't seen or heard her.) ...