Tech Tips, Tricks & Trivia

This Week I Learned -  *  Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database. *  Andrej Karpathy's review of Grok 3 - As far as a quick vibe check over ~2 hours this morning, Grok 3 + Thinking feels somewhere around the state of the art territory of OpenAI's strongest models (o1-pro, $200/month), and slightly better than DeepSeek-R1 and Gemini 2.0 Flash Thinking. Which is quite incredible considering that the team started from scratch ~1 year ago, this timescale to state of the art territory is unprecedented.   *  Thirukural dataset on Huggingface * To search on GitHub Communities for a user's posts - category:Copilot author:username * The Sydney-headquartered company Canva has more than 200 million users worldwide. India is Canva’s fourth largest market.  * Speed-watching is basically listening or watching content at accelerated speeds. YouTube updated c...

See more of my AI co-creations

This Week I Learned -  * Phi-4 is a 14B parameter state-of-the-art small language model (SLM) that excels at complex reasoning and conventional language processing. Phi-4 is available in GitHub Models. * You can now attach images and work with them directly in GitHub Copilot Chat. Share screenshots of errors and Copilot will interpret the image and resolve the issue.  * A group led by Elon Musk offered $97.4 billion to buy the nonprofit controlling OpenAI, aiming to prevent the AI startup from becoming a for-profit company. Musk co-founded OpenAI with Sam Altman in 2015 but left before it became successful. He later started a competing AI company, xAI, in 2023. OpenAI is trying to transition to a for-profit model to secure more funding for AI development. Musk sued Altman and others in August 2023, arguing they prioritized profit over public good. Musk believes OpenAI should return to its original mission of being open-source and focused on safety. * The gitingest service...

Summary of a recommendation from GitHub blog  (April 2025) Balance between cost and performance : Go with GPT-4.1, GPT-4o, or Claude 3.5 Sonnet. Fast, lightweight tasks : o4-mini or Claude 3.5 Sonnet Deep reasoning or complex debugging : Claude 3.7 Sonnet, o3, or GPT 4.5. Multimodal inputs (like images) :  Gemini 2.0 Flash or GPT-4o. Currently you can switch between 5 AI Models within the Copilot Chat interface. The OpenAI Models are hosted on Azure tenants. GitHub Copilot uses Gemini 2.0 Flash hosted on Google Cloud Platform (GCP). Claude 3.5 Sonnet is hosted on Amazon Web Services and so when you're using Claude 3.5 Sonnet, prompts and metadata are sent to Amazon's Bedrock service. When faced with options, I like asking all my AI assistants what they think. I liked the answer from Gemini. I added additional points from my own reading of the GitHub Copilot documentation & the answers from other AI assistants to come up with this analysis breakdown: 1. GPT 4o (...

Back in 2012, I was planning to build a location-aware app that would tell me about interesting sights & news-worthy facts about places that fall in the way of a train journey. I discovered that Web Dev guru Chris Heilmann ( @codepo8 ) had built a nifty app on a similar theme and shared the JavaScript code under the BSD license.  Things Around You used the browser's geolocation feature to find Wikipedia articles on nearby landmarks via the GeoNames API & list them with a brief description. For a Windows 8 app hackathon, I utilized the Geolocation detection idea to build a little app that I called GeoBuzz & posted it on the Windows 8 App Store. It's been on the back of my mind to extend it with more features. Now that GitHub Copilot is here, there was no need to procrastinate. I had a friendly chat with GitHub Copilot ( Gemini Flash model ). In under an hour, I customized @codepo8's original sample to include a map directly on the web page instead of linking t...

There is an exciting 4-Week Course on GitHub Community to help developers master GitHub Copilot & prepare for the GitHub Copilot Certification Exam . The threads contain a very useful curation of study material spanning the 7 Domains that will be covered in the exam & a knowledge check with practice questions for each of the 4 weeks. Click on the links below corresponding to the week numbers for the material. I plan to compile the reasoning for the answers to the practice questions here so that the notes can be quick reference for the exam & later - Week 1 GitHub Copilot is trained on publicly available open-source repositories and large proprietary datasets curated by GitHub. It does not use private repositories of individual users. Documentation and Stack Overflow discussions are not primary data sources for Copilot. GitHub Copilot enhance a developer's productivity during pair programming by providing inline code suggestions based on context Key ethical consideratio...

Chip Huyen is an AI engineering expert who has been in this field even before it was called AI engineering. She is the author of the O’Reilly book  AI Engineering . The chapter summaries of the book are available on Github . Chip has worked as a researcher at Netflix, was a core developer at NVIDIA (building NeMo, NVIDIA’s GenAI framework), and co-founded Claypot AI. She also taught Machine Learning at Stanford University. Q & A from her interview on The Pragmatic Engineer YouTube channel paraphrased by NotebookLM - Q: How would you define AI Engineer or AI Engineering? A: It's a shift from more machine learning to more engineering and more product . Previously, building machine learning applications required building your own models with your own data and expertise. Now, you can use direct API calls. Q: What are typical steps to build an AI application, from choosing a model through using RAG all the way to fine-tuning? A: Start by understanding what makes a 'good' vs...

See more of my AI co-creations

Writing for Developers: Blogs that get read by Piotr Sarna and Cynthia Dunlop My rating: 5 of 5 stars Technical writing and blogging may not come naturally to everyone. For many developers, the idea of putting thoughts into words can feel daunting. But the truth is, these skills are incredibly valuable whether you’re writing engineering blogs , presenting your work on platforms like GitHub or Kaggle, or simply communicating your ideas more effectively. The problem? There aren’t many resources out there to help developers master these skills. You could spend hours dissecting popular tech blogs, trying to decode their style and structure, or you could pick up a copy of " Writing for Developers " by Piotr Sarna and Cynthia Dunlop. Tech blogs and community forums are invaluable for developers. They bridge the gap left by the often dry and technical official documentation of software products and services. As a long-time blogger, I was thrilled to discover this book dedicated t...