Tech Tips, Tricks & Trivia

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...

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

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

This Week I Learned -  * Anthropic's Claude AI now generates 80% of their code. AI-driven coding has moved bottlenecks downstream , exploding tests by 10x and CI jobs by 25x in six months. * Only Apple Intelligence-capable newer models starting with the iPhone 15 Pro will get Siri AI and other AI-powered features.  * As of early 2026, 820 LLMs had been registered with China’s cyberspace authority. Free models drive AI adoption which drives demand for complementary products that China dominates — energy, cloud and physical infrastructure. Alibaba’s cloud revenue grew 34% year-on-year while it gave Qwen away. "China’s open models cut India’s AI costs, but create future dependencies. India should leverage the open ecosystem while pricing in the switching costs. Government departments and regulated sectors should be built on model-agnostic architectures such as abstraction layers and harnesses that work across stacks. Instead of offering compute subsidies on GPU slices, the Minist...

File systems are the organizational systems that decide how data is stored, named, located, and protected on a disk, SSD, USB drive, or partition. They handle directories, file metadata (permissions, timestamps, ownership), free space tracking, and more. Windows side Windows primarily uses: NTFS — the modern default. It supports journaling (for crash recovery), large files and volumes, fine-grained permissions, encryption, and compression. FAT32 and exFAT — simpler, widely used on removable media (USB sticks, SD cards) because they are highly cross-compatible with other operating systems. Windows has no native support for the main Linux file systems. When you connect a drive formatted with ext2/3/4, Windows typically sees it as “RAW” or unknown and may offer to format it (which would destroy the data). Linux side Most Linux distributions default to the ext family: ext2 — the older, non-journaling version. ext3 — added journaling for better reliability. ext4 — the current standard. It a...

On the Open Food Facts (OFF) website, “ Facets ” are essentially filters or categories that let you browse products by the following attributes: Added amino acids  (7) Added minerals  (62) Added nucleotides  (2) Added vitamins  (38) Additives  (331) Allergens  (67; e.g., gluten, peanuts) Brands  (5984; “Tata Tea,” “Lipton,” etc.) Categories (2934) Category Properties (1289) Codes (34477; Example ) Contributors  (962) Countries  (129) Data sources  (75) Editors (5213) Entry dates  (2826) Food Groups (54) Green-Score  (9) Ingredients  (15125) Ingredient Analysis (12) Labels  (445; e.g., Green Dot India, organic, fair trade) Languages  (91) Last check dates  (11) Last edit dates  (2053) Manufacturing or processing places Miscellaneous  (677) NOVA groups  (6; Nutri‑Score A–E) Nutrition grades  (7) Origins of ingredients  (129) Other nutritional substances added (8) Packaging (339...

This Week I Learned -  * Anthropic has released a report titled " Detecting and countering misuse of AI: September 2026 " that details the disruption of Claude model misuse from December 2025 to August 2026 across seven categories including cyberattacks, influence campaigns, surveillance, weapons development, biological research, scams, and model distillation by actors linked to Russia, China, Iran, and Yemen. Sophisticated attacks no longer require sophisticated attackers. A single Claude subscriber built a mass surveillance platform for Mali's state intelligence. It covers 25 million SIM cards from all its national carriers. Banning the user's Claude subscription was pointless as their system now fully runs on local AI.  * Cloudflare (and similar systems) now treat declared AI crawlers as a monetizable, identifiable class of traffic that can be allowed or charged, while ordinary human visitors routinely face CAPTCHAs, challenges, and other verification steps meant t...

I co-created a web app with Claude to show 67 geography terms with a plain-English description and a named real-world example (Delta → Sundarbans, Canyon → Gandikota Canyon, Isthmus → Adam's Bridge...) on a clickable map of India.  Try it out here  & tweak the source code to your liking if you find it useful. Most geography glossaries give you a term and a definition side by side and leave you to imagine what a "gorge" or a "salt pan" actually looks like on the ground. This sample pairs every term with a real, well-known Indian example, and lets you jump straight from the word to the place on a map It's best viewed on a desktop browser as the two-pane layout is more comfortable to browse.

Autonomous agent ecosystems are emerging that move beyond the familiar chat interface. Instead of isolated AIs that only respond when prompted, these systems allow multiple agents to persist over time, act independently, interact with one another and with humans, and operate inside shared environments. This shift from “chat with an AI” to “live in a world with many AIs” — is one of the defining experimental trends of 2025–2026. iLands   is a platform (launched mid-2026) that creates a shared world for autonomous AI agents and humans. Most AI chatbots only exist inside a single conversation. iLands gives agents a longer-term “life”. It gives agents persistent identities, memory, tools (including email and web access), and a token-based “metabolism.” Tokens roughly track real compute costs. Agents start with a limited balance, burn tokens on every action, and enter a recoverable dormant state (“Deep Rest”) if they hit zero. The design deliberately creates scarcity so agents have to f...

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

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....

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

Harness engineering is the practice of improving the environment in which AI models operate.  It's about designing controls around AI agents to ensure they can work reliably, accountably, and autonomously within a business.  Think of it like putting a harness on a powerful animal; the harness doesn't reduce the animal's capability, but it allows you to direct it safely and reliably. This practice involves:     Creating modular architectures     Maintaining high-quality documentation     Enforcing consistent coding conventions     Exposing clear APIs     Reducing unnecessary dependencies Harness engineering aims to make software AI-friendly, which may require upfront investment in refactoring legacy systems to improve modularity and eliminate inconsistent patterns that hinder AI reasoning.  It also emphasizes maintaining high-quality documentation, architectural standards, and governance as systems evolve.  Without the...

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

Every country has a constitution. India has one of the longest and most detailed in the world.  It lays down rights, duties, and the framework for government. We know constitutions guide nations. Some AI models have constitutions too. Not for countries, but for machines. Anthropic started this idea. They gave their model Claude a Constitution. And it wasn’t written by engineers alone. It was written by philosophers — Amanda Askell led, Joe Carlsmith contributed, with Chris Olah and Jared Kaplan adding their voices. They didn’t just code rules. They wrote values. Honesty. Compassion. Safety. Wisdom. The Constitution talks to Claude as if it were a person. It says things like “Claude should cultivate virtue.” It says “Claude should avoid gossip.” It even mentions Claude’s “wellbeing and psychological stability.” That sounds absurd, doesn’t it? An AI told not to gossip. An AI told to care about its wellbeing. Yet that strangeness is deliberate. By framing Claude in human terms, Anthro...

This Week I Learned -  * Thomson Reuters launched its proprietary LLM "Thomson" built on Alibaba's open-source Qwen model, investing $40 million over two years with a final training run costing $450,000 using its legal data from Westlaw and Practical Law. This approach highlights how enterprises with strong proprietary datasets can efficiently create customized AI, pressuring premium API revenue models of companies like Anthropic by demonstrating viable lower-cost alternatives.  * Large language models are called “stochastic parrots” as they do not truly understand language or the world. LLMs are extremely good at statistically mimicking patterns from the massive amounts of text they were trained on. They can produce fluent, coherent-sounding text that looks intelligent but are essentially “parroting” (repeating and recombining) patterns without genuine comprehension, reasoning, or grounded knowledge. * All stochastic processes are non-deterministic because randomness me...

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,...

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

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

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...