Tech Tips, Tricks & Trivia

See more of my AI co-creations

Front-end leaders share their experience on pushing the boundaries of Web AI and run machine learning models entirely client side in the browser via JavaScript to get privacy, lower costs, and lower latency. From traditional AI models to Generative AI such as large language models (LLMs) and diffusion models, discover the latest advances of Web AI in 2024 that are accelerated by technologies such as WebAssembly, WebGPU, and WebNN.

Lately, I’ve found YouTube DIY videos incredibly handy for fixing small issues around the house. Beyond saving money, the real reward has been the satisfaction of understanding how household items work. It’s amazing how people from remote places are helping DIY-ers solve problems through well-explained videos and how with the magic of AI, the auto-dubbing feature on YouTube is making these videos accessible to an even wider audience. Back in September, I learned from a YouTuber in Karnataka how to troubleshoot a portable fan that had stopped working and then replace and wire up a new rechargeable lithium-ion battery to bring it back to life.  A YouTuber from Himachal Pradesh helped me fix a leaking and overflowing commode cistern. YouTube is indeed a great learning tool!

Cartoon co-created with ChatGPT. See more of my AI co-creations

An Edge user reported on Microsoft Q&A that the Read Aloud feature is not working with PDFs and therefore came up with this workaround - Select all the text (Ctrl+A) and copy it (Ctrl+C) from the PDF. Open a new tab and paste (Ctrl+V) the text into an online editor, such as https://onlinenotepad.org/notepad  (uses Web Storage API to automatically save your notes). Use the "Read Aloud" feature in this new tab on the web page, since it usually works on regular web page text. The steps in the workaround could be used with any content that you can copy and paste!  Since Microsoft introduced this feature, content can be “Read Aloud” in various voices of your choice and can also be used with non-English content . The same Microsoft Q&A thread also reveals that the Read aloud feature in Microsoft Edge is implemented through the Microsoft Voice (Speech Recognition) component/extension.  If the Read aloud feature is not appearing for you, you can verify if the extens...

Gartner defines AI code assistants as tools that generate and analyze software code and configuration.   LEADERS GitHub Amazon Cognition (Windsurf) Gitlab Google Cloud CHALLENGERS Anysphere (Cursor) Alibaba Cloud VISIONARIES Tencent Cloud IBM JetBrains NICHE PLAYERS Harness Qodo Tabnine Augment Code Notes - Alibaba Cloud’s Lingma roadmap and product design focus heavily on Qwen, the company’s proprietary model, with little attention given to offering model choices or fostering broader ecosystem flexibility. AWS shows impressive innovation by bringing its AI features to a variety of IDEs like its new AI-native IDE, Kiro as well as to terminals and DevSecOps platforms with integrations for GitHub and GitLab. It has also led the way with specialized agent solutions, especially its modernization-focused code transformation agent . Cursor has a solid history as an early innovator, bringing in features that have since become key to AI-native IDEs. Augment Code shines when it comes to c...

Today's AI coding tools look like fierce competitors, but they're all built on each other's work.  Today’s AI-powered IDEs like Cursor, Windsurf, Kiro and many others all stand on the giant shoulders of open-source work contributed by companies that once battled each other in the browser wars.  Windsurf, for example, is a fork of Microsoft’s VS Code. VS Code itself runs on Electron, which is built on top of Chromium and Node.js. Chromium comes with Google’s V8 JavaScript engine and uses Blink, a fork of Apple’s WebKit.  So even when Google, Microsoft, GitHub, and Apple compete publicly, their code ends up powering each other’s tools behind the scenes. Open source has turned “tech rivals” into “reluctant collaborators,” whether they planned it or not. The AI Model Dependencies The same pattern exists with AI models. Competing IDEs use each other's models, hosted on each other's clouds. GitHub Copilot (Microsoft) uses : OpenAI models (GPT-4.1, GPT-5 family) - hosted o...

Kai-Fu Lee, Chairman of Sinovation Ventures and author of  AI Superpowers and  AI 2041: Ten Visions for Our Future on the China-US AI Race Q: There's still a lot of challenges when it comes to the whole monetization of AI, according to his perspective. In the last three years, though, how have you looked at this whole evolution of China AI versus the US, and what are the advantages and challenges for China? A: Yeah, so firstly, I disagree on the prospects for the USA. USA because yes, you look at OpenAI, it's making half billion spending 40 billion. It looks like a bad balance sheet, but most of that 40 billion is spent for future revenues. And if you believe there are 2x, 3x, 5x growth for the next three years, it's going to justify that valuation at some point. The bubble is merely that it's gotten ahead of itself, not the likelihood of growth in the future. Not saying it's worth its price, right, but there's absolute substance under the thumb. Now back to t...

Cartoon co-created with ChatGPT. See more of my AI co-creations

Cartoon co-created with Perplexity. See more of my AI co-creations

* Every AI application startup is likely to be crushed by rapid expansion of the foundational model providers. The foundational provider introduces continual chaos into the entire ecosystem at a rate never before seen, to a degree such that downstream providers can never get established.  It’s not a one-time sea change, it’s continual tsunamis. There are two ways AI application startup founders can make money: - Make a flash-in-the-pan app that generates a ton of cash and bank the cash (my estimate is that you have about 12-18 months cashflow generation) - Make a good enough app that you get acquired by one of the big players for sufficient equity Sea changes are now happening on a 9-12 month cycle. Very few startups can turn into a mature business in that timeframe - and by mature, I mean having all the boring stuff like sales relationships and brand recognition. The physical moat is the only one that's like "large rocks that can offer cover from the continually crashing wave...

21 Lessons 00:00:00 - Introduction to Generative AI and LLMs [Pt 1] 00:10:36 - Exploring and comparing different LLMs [Pt 2] 00:31:34 - Using Generative AI Responsibly [Pt 3] 00:40:54 - Understanding Prompt Engineering Fundamentals [Pt 4] 01:04:08 - Creating Advanced Prompts [Pt 5] 01:21:06 - Building Text Generation Applications [Pt 6] 01:36:37 - Building Chat Applications [Pt 7] 01:50:10 - Building Search Apps Vector Databases [Pt 8] 02:08:08 - Building Image Generation Applications [Pt 9] 02:30:32 - Building Low Code AI Applications [Pt 10] 02:46:55 - Integrating External Applications with Function Calling [Pt 11] 02:56:06 - Designing UX for AI Applications [Pt 12] 03:08:38 - Securing Your Generative AI Applications [Pt 13] 03:16:49 - The Generative AI Application Lifecycle [Pt 14] 03:29:12 - Retrieval Augmented Generation (RAG) and Vector Databases [Pt 15] 03:40:03: - Open Source Models and Hugging Face [Pt 16] 03:51:32 - AI Agents [Pt 17] 03:59:26 - Fine-Tuning LLMs [Pt 18] Relate...

Cartoon co-created with ChatGPT.  See more of my AI co-creations

Kaggle and Google are running a 5-day Gen AI Agents Intensive course with daily assignments and lectures from November 10 to 14, 2025.  Start with the  self-paced learning guide  or just check the highlights & key links below. Also see -  Kaggle's 5-Day Gen AI Intensive Course - Notes Notes - "It's not the year of the agent. It's the decade of the agent." - Andrej Karpathy Introduction to Agents Building successful agents isn't just about having the smartest model. The Agent is the combination of the model for reasoning, the tools for action and the orchestration layer managing that loop. Success hinges on the architecture, governance, security, testing, observability An agent can do more than just respond to a prompt — it can take actions to find information or get things done. Whitepaper:  Introduction to Agents Codelabs: Build your first agent using Gemini and ADK - From Prompt to Action Build your first multi-agent systems using ADK - Agent Architec...

WhatsApp from Meta is a free messaging and video calling app. It’s used by over 2B people in more than 180 countries. * WhatsApp was launched in May 2009 by Brian Acton (born 1972) and Jan Koum (born 1976).  Koum chose the name WhatsApp because it sounded like "what's up". The idea started off as an app that would display statuses in a phone's Contacts menu, showing if a person was at work or on a call.  * Apple introduced push technology in June 2009, enabling users to receive notifications even when not actively using the app. Koum modified WhatsApp so that everyone in a user's network would be alerted when their status changed. Surprisingly, users began using this feature to send playful custom statuses like "I woke up late" or "I'm on my way" to each other. * After becoming a computer science graduate from Stanford University, Brain Acton tested products at the Apple Inc. and Adobe Systems, before joining Yahoo as its 44th employee in ...

This Week I Learned -  * The AI boom is minting billionaires. There are around 500 AI unicorns already, and just the top four had created 15 billionaires by March. Last week added three more, an unremarkable figure when four billionaires (of all kinds) are added every week, on average. But 22-yearold Adarsh Hiremath, Surya Midha and Brendan Foody are the youngest self-made billionaires ever . By breaking Mark Zuckerberg’s 2008 record – he was 23 then – they’ve become the tech world’s equivalent of Renaud Lavillenie, who smashed Sergey Bubka’s two-decade-old pole vault record in 2014. John Rockefeller, the first dollar billionaire, was 77 when he hit the mark in 1916. Since then, the median age at which people amass their first billion has slipped to 67. Anyone who makes it by 50 is still considered ‘young’, because only about 10% of the world’s 3,500-odd billionaires form that cohort. Self-made tech billionaires are at greater risk because of the nature of their wealth – valuations...

See more of my AI co-creations

Dheemanth Reddy and Bharath Kumar from Maya Research AI have developed an open-source, world-class voice conversational models  from their SPC Bengaluru office in HSR Layout. Their 3B parameter Maya1 model is open-weight and was trained entirely using free compute credits. Anyone can download the model, inspect it, use it, or fine-tune it. It’s not locked or proprietary like many large AI models. The model can understand speech and respond in natural sounding speech — similar to Siri, Alexa, or GPT voice chat. The model is strong enough to be compared with leading voice AI models, despite being built with minimal resources. Core Capabilities: 20+ emotional styles (e.g., cheerful, calm, dramatic). Zero-shot voice design - clone or design new voices without needing training data. 3B-parameter architecture, optimized for production-ready real-time streaming. Apache 2.0 license - businesses can deploy and monetize with no per-usage fees . Supports fine-tuning to create un...

This Week I Learned -  * SLMs are generally under 12B parameters and can outperform larger models for specific agentic-related tasks like RAG, tool calling, structured decoding, and programmatic tool use. *  A new study by international researchers finds leading AI models are about 50% more sycophantic than humans, affirming users’ actions even when they involve manipulation or harm. Carried out by researchers from Stanford University and Carnegie Mellon University, it introduces the term “social sycophancy” – a form of AI behaviour that flatters a person’s selfimage or actions instead of being factual. This kind of subtle affirmation, experts argue, poses deeper psychological and social risks than mere factual errors. Across 11 widely-used large language models (LLMs) — including those from OpenAI, Anthropic, Google, Meta and Mistral — researchers found that AI systems consistently validated user behaviour more readily than human advisers. When presented with moral or relatio...