Tech Tips, Tricks & Trivia

This Week I Learned -  * Nikhil Pahwa on  how to use AI to write without the slop : Step 1: Find something you want to write about and record a voice note (transcribe it) or collect information/news articles about it. Step 2: Feed this voice note / notes to AI, whether ChatGPT or Claude, and ask it to identify 20 questions for you. The rule: no questions to which the answer is yes/no or one of a few options. Step 3: Record a voice note answering the questions. you don't need to answer all the questions. Feel free to ramble, and anything above 10 minutes is good. Anything over 20 minutes is amazing.  Step 4: Give your voice note transcript to AI. Ask it to identify a structure from the questions you've answered or simply, ask AI to structure your talk into an article structure verbatin with subheads. Important instruction: "do not paraphrase, do not add filler or transition sentences". Step 5: once you have a structure you like, edit the transcript to tighten language....

This Week I Learned -  * According to AI-ML guru Andrew Ng, these are the four most important AI engineering skills: Building and deploying AI applications Software engineering fundamentals Using coding agents Shaping the build * GitHub has rebuilt Copilot review around an agentic architecture that gathers broader repository context, uses tools, produces findings, and can hand fixes to another coding agent. This is substantially more than autocomplete added to old review. - The GitHub Blog * Shadow AI refers to consumer-facing AI applications and standalone agents deployed across your organization without IT visibility or approval. These agents can operate autonomously on user devices, creating blind spots in your security and compliance posture.  Microsoft now ships specific discovery, monitoring and governance for unmanaged AI agents. Shadow AI blocking currently apply only to managed Windows devices enrolled with Microsoft Intune. * AI can boost learning productivity,...

This Week I Learned -  * When unconstrained, the AI model can draw from numerous sources to assess its options on how to proceed in answering a prompt, thereby allowing widely varying outcomes. Any foundational decisions or other instructions—artifacts collectively known as “ provenance ” when properly preserved—which were formulated during the original context session and then cleared, are lost. This is the key deficiency of vibe coding which spec-driven development and context engineering seek to address. Context engineering moves a developer from a vibe coding technique to a structured approach to generating code that preserves provenance using key artifacts. This allows context to be restored by other developers, reviewed by other stakeholders, or retrieved at any point if someone wanted to audit the inputs that generated a given codebase or simply wanted to continue building upon them. Different methodologies have emerged that offer different perspectives on how to effectively...

This Week I Learned -  * " Models learn from "exhaust," the prompts people write, the tools agents use, and especially the corrections people make when the model is wrong. Every correction is distilled into institutional know-how.  In consuming intelligence, you are creating intelligence. If learning flows in only one direction, economic value converges toward the owners of the learning infrastructure rather than the creators of the knowledge itself. In the cloud era, enterprises accumulated data. In the AI era, they accumulate learning. A company should be able to use a model without giving up the knowledge that makes it unique. " - Satya Nadella * Wire services such as PTI, ANI, Reuters, AP, and AFP provide verified facts to other outlets, which then adapt the content to their own style. Their business model depends on reader trust in the accuracy of the wire’s reporting and on receiving compensation for the verification work. While search engines direct readers t...

This Week I Learned -  * The OpenRouter Pareto Router is a dynamic model selection tool that allows users to select a coding model based on a minimum coding score preference. It maintains a curated shortlist of strong coding models ranked by Artificial Analysis coding percentiles. Users can set a min_coding_score between 0 and 1 to control the strength of the coder they need. The router automatically selects the cheapest model within the chosen tier or the fastest with the Nitro variant. This approach ensures that users receive a strong coder without overspending, as the exact shortlist evolves over time with new models and benchmarks. The OpenRouter API is compatible with most SDKs, allowing for easy integration into applications. * openrouter/auto-beta is a task-aware router. It classifies each request, routes it to the model teams are actually spending on for that kind of task, and filters that choice by the cost-quality tradeoff you set. The response is priced at the routed mo...

This Week I Learned -  * Microsoft's Phi-4 Mini is widely regarded as one of the most capable models under 4 billion parameters. It punches significantly above its weight class, outperforming older 7B and even 70B models in specific reasoning tasks. It runs at a smooth 13–18 tokens per second on flagship devices with 8 GB+ RAM (like the iPhone 16 Pro/17 Pro or Galaxy S25/S26 series). * From The Batch : - PrismML, a Caltech spinout backed by Khosla Ventures, publicly released compressed versions of Alibaba’s Qwen model on Tuesday, shrinking it from 54 GB to under 4 GB so all 27 billion parameters run on an iPhone (15 or newer). PrismML achieves the compression by reducing the models to ternary or binary quantization, reducing each value from 16 bits to just two or three possible values.   - Two people asking the same model for business feedback, one in Hindi and one in Russian, may receive substantively different advice not because they’re using different models, but because th...

This Week I Learned -  *  arXiv offers HTML papers alongside the existing PDF to improve accessibility . * " Students need to learn how to work with AI, recognize weak output, think through choices, test results and decide what is worth doing. I described my own approach as “delegate maximally”. Instead of keeping a fixed list of AI-proof skills, keep giving AI everything it might be able to do. Whatever remains is the human role for now. " - S Anand * " The reason I dislike this emphasis on term “LLM Visualization” or “Claude Viz” or even “Agentic Viz” is the focus on the tool. No one goes out and says “Excel Viz” // “PowerPoint Viz” // “Figma Viz”. The tool is there to augment the human and has never been the important part.  The craft and skill of the  human using the tool is what we should acknowledge and celebrate. " - Amit Kapoor * Draw with Data by Schubert De Abreu   * Bharat Atlas is a lightweight open-source visualiser for India administrative boundar...

Open Food Facts has data on 4.6+ million food products worldwide. There are multiple ways to access that data but the simplest way to get a subset of the data with chosen parameters is to  download it as a CSV file  through the website's search interface. But if you need entire data for one country, you can filter the  7.64 GB file  (size at the time of writing) hosted on Hugging Face as there are no natively available exports dedicated to specific countries currently . Hugging Face acts as a CDN for large ML datasets — it not only stores the full Parquet file but also handles versioning, caching, and fast global downloads. This guide co-written with Meta AI shows you how to use Google Colab to filter the dataset for just one country, add direct product links, and save the result to a public GitHub repo. Takes < 30 minutes total based on your familiarity with these tools & file size. No software installs needed. What you’ll end up with: A CSV like india_pr...

This Week I Learned -  *  Intensive Vibe Coding Course With Google - self-paced Kaggle Learn guide * Forward Deployed Engineers (FDEs) bridge internal development and real-world deployment by embedding with enterprise clients to build solutions while guiding the product roadmap.  FDEs are the "Technical Special Ops" who bridge the gap (The Delta) between a core product and a client’s messy, real-world reality. * Google DeepMind CEO Demis Hassabis and researcher John Jumper won the Nobel Prize in chemistry for their work on the company’s AlphaFold model, and DeepMind has also made major contributions to meteorology, materials science, and a variety of other disciplines. John Jumper is leaving DeepMind for Anthropic.  * Like Claude Code, Claude Science can autonomously carry out meaningful work when given concise, high-level instructions, and it has access to tools that make it particularly useful for research in computational biology and drug development. C...