Software naming has power. I first became aware of this when a friend commented how much he enjoyed starting Windows 3. “Win,” he said. “I just love typing that!” I felt this this again recently with just. just lint Can you feel it? just build Actually, I just like to say “Just…” just test
I was a panelist at the PyConf Hyderabad AI in SDLC - Panel Discussion. After that, one of the volunteers asked for a video interview. “How was the panel discussion?” he asked. Ever since I started using AI actively, my brain doesn’t work without it. So, instead of an eloquent answer, I said, “Good.” He tried again. “Um… how did you feel about it?” he asked. I searched for my feelings. Again, fairly empty in the absence of AI. “Good,” I said again. ...
Yesterday, I was part of an IIM Bangalore interview panel at Hyderabad, along with Professor Subhabrata Das and Debajyoti. Panels typically comprise of two faculty and an alumni, and handle 8 interviews in the morning and eight in the evening, though in our case, we had 9 each. As we arrived, we were given a USB drive with the student’s resume, statement of purpose, and other documents that they had submitted, which included employment contracts, declarations, letters of recommendation, etc., depending on the student. Each interview was approximately 20 minutes. Luckily, Dr Das set a timer for 18, so we didn’t go too far beyond. ...
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 shared a photo of my right hand with popular AI agents and asked for a detailed palmistry reading. Apply all the principles of palmistry and read my hand. Be exhaustive and cross-check against the different schools of palmistry. Tell me what they consistently agree on and what they are differing on. I was more interested in how much they agree with each other than with reality. So I shared all three readings and asked Claude: ...
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. ...
An effective way to solve online exams is to point a coding agent at it. I use that on my Tools in Data Science course in two ways: As a test case of my code. If my agent can solve it, good: I set the question correctly. As a test of student ability. If it can’t, good: it’s a tough question (provided I didn’t make a mistake). For PyConf, Hyderabad, my colleague built a Crack the Prompt challenge. Crack it and you get… I don’t know… goodies? A job interview? Leaderboard bragging rights? ...
I often research how the world will change with AI by asking AI. Today’s session was informative. I asked Claude, roughly Economics changes human behavior. As intelligence cost falls to zero, here are some changes in my behavior [I listed these]. Others will have experienced behavioral changes too. Search online and synthesize behavioral changes. It said this. 🟡 People spend time on problem framing & evaluation. AI can execute the middle. (I’m OK at this. Need to do more framing + evaluation.) 🟢 People don’t plan, they just build. (I’m prototyping a lot.) 🟢 People build personal data & context. (I’m mining my digital exhaust.) 🔴 People queue work for agents, delegating into the future. (I’m not. I need to do far more of this.) 🟢 People shift from searching to asking for answers. (I do this a lot, e.g. this post.) 🟡 People are AI-delegating junior jobs and developing senior level taste early. (Need to do more.) 🟡 People treat unresolved emotions as prompts. (Need to do more.) Rough legend: 🟢 = Stuff I know. 🟡 = I kind-of know. 🔴 = New learning. ...
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. ...
I maintain an LLM art style gallery - prompts to style any image I generate. Since I generate several comics, I added a comic category page that includes styles like: To generate these, I asked Claude: Here are some examples of image styles I've explored. <image-styles> "2D Animation": "2D flat animation style, clean vector lines, cel-shaded coloring, cartoon proportions" "3D Animation": "Modern 3D animation render, smooth surfaces, dramatic lighting, Octane render quality, cinematic depth" ... </image-styles> In the same vein, I'd like to explore **comic** styles. Create 30 popular comic / cartoon styles, aiming for diverse aesthetics and cultural influences. Name it concisely (1-2 words) based on the source, but the description should not reference the source directly (to avoid copyright issues). Focus on the visual characteristics that define each style. Pick those KEY visual elements that will subliminally evoke the style without explicitly naming it. … followed by: ...
I added a narrative story to my LLM Pricing chart. That makes it easier for me and others to tell the story of AI’s evolution in the last three years. Video It was vibe-coded over two iterations. In the first version, I prompted it to: Add a scrollytelling narrative. So, when users first visit the page, they see roughly the same thing as now (but prettier). As they scroll down, the page should smoothly move to the earliest month, and then animate month by month on scroll, and explaining the key events and insights in terms of model quality and pricing. Use the data story skill to do this effectively, narrating like Malcolm Gladwell, with the visual style of The New York Times, using the education progression as a framework for measure of intelligence (read prompts.md for context). Store the narrative text in a separate JSON file and read from it. This should control the entire narrative, including what month to jump to next, what models to highlight, what insights to share, and so on. ...
People worry that AI atrophies skills. Also that junior jobs, hence learning opportunities, are shrinking. Can AI fill the gap, i.e. help build skills? One approach is: Do it without AI. Then have AI critique it and learn from it. (Several variations work, e.g. have the AI do it independently and compare. Have multiple AIs do it and compare. Have AI do it and you critique - but this is hard.) ...
After an early morning beach walk with a classmate, I realized I hadn’t taken my house keys. My daughter would be sleeping, so I wandered with my phone. This is when I get ideas - often a dangerous time for my students. In this case, the idea was a rambling conversation with Claude that roughly begins with: As part of my Tools in Data Science course, I plan to create a Cloudflare worker which allows students to play a game using an API. The aim is to help them learn how to build or use AI coding agents to interact with APIs to solve problems. ...
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’ve long felt that while the Gemini 3 Pro model is fairly good, the Gemini CLI harness isn’t. I saw an example of this today. Me: Tell me the GitHub IDs of all students in this directory. Gemini CLI: SearchText 'github' within ./ Found 100 matches (limited) Sending this message (14606686 tokens) might exceed the remaining context window limit (1037604 tokens). Me: Only send the (small) required snippets of data. Write code as required. ...
STEP 1: I asked Nano Banana 2 (via Gemini Pro) to: Imagine and draw a photo that looks ultra realistic but on a closer look, is physically impossible, and can only exist because images are a 2D projection that we extrapolate into three dimensions. Avoid known / popular illusions or images of this kind, like Escher’s work, and create something truly original. Think and draw CAREFULLY! … six times, followed by “Suggest a name for this”. ...
In my graded assignments students can pick an AI and “Ask AI” any question at the click of a button. It defaults to Google AI Mode, but other models are available. I know who uses which model and their scores in each assignment. I asked Codex to test the hypothesis whether using a specific model helps students perform better. The short answer? Yes. Model choice matters a lot. Across 333 students, here’s how much more/less students score compared with ChatGPT: ...
When I was in class 8 or 9, our English teacher told us a story I’ll never forget. There was a poor farmer who lived in a village. He owed the zamindar (landlord) of the village a lot of money. The zamindar had an eye on his daughter. “Marry your daughter to me, and I’ll forgive your debt,” he said. The farmer was reluctant. “Please, sir, what will the village say about your marrying such a young girl?” he asked. ...
I was watching Vasu while Codex-ing and came across this dialogue: Here’s the dialogue, recorded via ffmpeg, transcribed via AI Studio: మీ నాన్న మిమ్మల్ని పోలీస్ ఆఫీసర్ అవ్వమని అడిగితే అయ్యారా? మీకు ఇష్టం కాబట్టి అయ్యారు. సచిన్ టెండూల్కర్ ని ఇంజనీర్ ని చేయాలని వాళ్ళ నాన్న అనుకుని ఉంటే, ఇండియా ఒక గొప్ప క్రికెటర్ ని మిస్ అయ్యేది. విశ్వనాథ్ ఆనంద్ ని డాక్టర్ ని చేయాలని వాళ్ళ అమ్మ కోరుకుని ఉంటే, ఇండియాకి ఓ గ్రాండ్ మాస్టర్ ఉండేవాడు కాదు. ...
Instead of learning and applying new Codex features, I asked it to analyze my sessions and tell me what I’m under-using. I'd like you to analyze my Codex sessions and help me use Codex better. sessions/ has all my past Codex sessions. Search online for the OpenAI Codex release notes for the latest features Codex has introduced and read them - from whatever source you find them. Then, create a comprehensive catalog of Codex features. Then, analyze my sessions and see which feature I could have used but didn't and make a comprehensive list. Then summarize which features I should be using more, how, what the benefits are, and with examples from my sessions. Document these in one or more Markdown files in this directory. Write scripts as required. Commit as you go. It did a thorough job of listing all the new features and analyzing my gaps. ...