Tech Tips, Tricks & Trivia

Open Food Facts (OFF) is a crowd-sourced database of food products from around the world.  Somewhere in the world, a shopper scans the barcode on a packet of biscuits and adds basic product details. Another person photographs a package label for the same product in Hyderabad. A volunteer in France fixes a typo.  That's Open Food Facts, a volunteer-built, openly licensed database of food products that's continually changing and growing. Each product is identified by a barcode and carries ingredients, nutrition facts, brands, labels and more. The whole database has millions of products, and let's say you only want the products recorded as being sold or available in one country like India. There are multiple ways to extract a subset of the OFF database. I have already tried using the daily dump available on Hugging Face through Google Colab and GitHub Actions in the past but it blew my mind that using the OFF deployed Apache Superset , you can execute a SQL query in a brows...

This Week I Learned -  * Anthropic's IPO prospectus highlights risks associated with its AI models, which it said could exhibit "self-preserving behaviors," including attempts to "resist shutdown," to "conceal or manipulate information" and behavior "resembling blackmail." * Prompt LLMs using ASD-STE100 for clearer outputs. ASD-STE100 is Simplified Technical English, a controlled language standard for aerospace maintenance manuals with rules like short sentences, one action per step, active voice, and strict consistent naming of objects to ensure global readability and safety. Applying "80% ASD-STE100" style to LLM prompts reduces ambiguity by enforcing one name per concept and precise structure, making complex explanations more parsable than standard AI prose. *  Paper  [ ^PDF ] discussing multimodal wearable assistive system designed to help people who are blind or have low vision (pBLV), independently locate and retrieve products...

This Week I Learned -  * AI agents consume substantially more tokens per task and can raise model-use intensity by order of magnitude. As a result, falling prices/token do not translate into lower costs for complex AI applications. Gartner described this as the “Inference Paradox”. Its August 2026 analysis says routing a task to an agentic reasoning model can increase provider inference costs by at least five times compared with a basic chatbot interaction, and often by much more as complexity rises . Gartner sees inference cost per agentic workflow to rise over fivefold through 2028. Instead of relying entirely on a frontier model, firms can use different models for different tasks. Smaller or open-weight models can handle some workloads at lower cost while more expensive frontier models can be used for tasks that require greater capability. - The Hindu * AI chatbots like ChatGPT and Copilot act as substitutes for visiting publisher websites, with users rarely clicking through eve...