Anantha @ananthsubklt

Cancer patient was about to die. She pleaded. Her plea has been listed 57 times. The court has still not heard it. Teesta Setalvad was about to be jailed. She pleaded. Her plea was listed out of turn. The court heard it at midnight. Cancer patient is dead. Teesta is alive.

Lately, I've been seeing quite a few posts and videos about the Mahua tree. Naturally, I became curious to learn more about it. The Mahua tree is revered as the Mother Tree, and its flowers are the OG sweeteners of India! 😎 It has been an integral part of the lives of tribal communities across central India for generations. Almost every part of the tree has a purpose -from its flowers to its seeds, leaves, and bark. In folk traditions, it is also valued for supporting digestion and overall well-being. A remarkable tree that has been cherished for generations. Tagging @NaturallySudha , who shares so much about our trees, flowers, and soil. 😊 vc Instagram /monksbouffe

Zero deaths. That is the mission. A dedicated team of forest officers, patrolling staff, loco pilots, drone operators and control centre monitors works round the clock at Tamil Nadu’s AI-powered Elephant Control and Command Centre in Madukkarai in Coimbatore to keep elephants safe. In just over two and a half years, the system has facilitated around 9,481 safe elephant crossings ensuring Zero elephant deaths on Railway Tracks, demonstrating how technology, human vigilance and teamwork can come together to protect wildlife. The system has generated more than 7,116 real-time alerts for railway authorities and loco pilots, leading to 3,821 instances where trains were slowed down or stopped to allow elephants to cross safely. Beyond elephants, the system has also detected deer, gaurs and leopards, creating a comprehensive AI-enabled wildlife monitoring network. The Government of Tamil Nadu continues to strengthen the system. AI-powered drones have been deployed for wider landscape surveillance, extending monitoring beyond fixed thermal cameras and providing real-time situational awareness of elephant movements. No system can ever be perfect, and the worry never really goes away. But we must keep learning, improving and doing better. A big shoutout to these unsung heroes whose constant vigilance, dedication and hard work make this possible. #AIMadukkarai #AIForWildlife #Elephants #WildlifeConservation

The Vellamalai Tunnel River is a scenic, offbeat water channel in Valparai, Tamil Nadu. Located about 3 km from Valparai town, it features pristine freshwater flowing gently over a bed of small pebbles through tea estates and rocky tunnels. Video credits to Valparai paradise page 🙏

"என்னப்பன் எம்பிரான் எல்லார்க்குந் தானீசன் துன்னம்பெய் கோவணமாக் கொள்ளுமது என்னேடி?"🪷 திருமுறை பாடுவதை கேட்கவே பேரானந்தம்!! 😇🙏 மற்ற கலைகளோடு தேவாரமும் ஈஷா சம்ஸ்க்ருதி பள்ளியில் மாணவர்கள் கற்றுக் கொள்கிறார்கள் என்பது மிகவும் மகிழ்ச்சியளிக்கிறது. நம் பாரம்பரியம் இப்படித் தொடர்வதைப் பார்ப்பது மனநிறைவைத் தருகிறது. ❤️ vc : IG /pannisai_deva

Sam Altman, CEO of OpenAI: "To build with AI, you don't need a huge team. You need a good idea." In a 52-minute keynote, he describes how building stopped requiring a company behind you. For the first time, one person with a setup can produce what used to take a floor of staff. That's the shift making the first people rich alone, without a single hire. Watch the keynote, then see the one thing they learned in the article below. Bookmark this one.

Zephyr @Zephyr_hg

a week ago

x.com/i/article/2072…

1 25 213 298K 622

A harnessed LLM agent, clearly explained! Most people picture this as a model with tools bolted on. The real architecture inverts that relationship. The model itself is deliberately thin. Intelligence gets pushed outward, and the harness composes it at runtime. Three dimensions orbit the harness core: - 𝗠𝗲𝗺𝗼𝗿𝘆 holds the state a model shouldn't carry in weights or context. Working context, semantic knowledge, episodic experience, and personalized memory each have their own lifecycle. - 𝗦𝗸𝗶𝗹𝗹𝘀 hold procedural knowledge. This can cover operational procedures, decision heuristics, and normative constraints that specialize the general model per task. - 𝗣𝗿𝗼𝘁𝗼𝗰𝗼𝗹𝘀 hold the interaction contracts. Agent-to-user, agent-to-agent, and agent-to-tools are three distinct surfaces with their own failure modes. Between the core and these modules sit the mediators, like sandboxing, observability, compression, evaluation, approval loops, and sub-agent orchestration. They govern how the harness reaches out and how state flows back in. The useful question this framing unlocks is: for any new capability, where should it live? - Stable knowledge goes to memory - Learned playbooks go to skills - Communication contracts go to protocols - Loop governance goes to the mediators Harness design becomes a question of what to externalize, and how to mediate it. We wrote an article about the anatomy of Agent Harness, covering the orchestration loop, tools, memory, context management, and everything else that transforms a stateless LLM into a capable agent. Read it below.

Akshay 🚀 @akshay_pachaar

3 months ago

x.com/i/article/2040…

82 563 3K 2.3M 8K

A shortfilm on "Samosa" in Tamil. Just 70 seconds, but superb end... 😄👌

🚨 India's Manav Thakkar & Manush Shah beats World Champion Togami & Matsushima 🤩🔥 The Indian duo defeated Top Japanese Pair 3-1 in the Round of 16 at United States Smash! WELL DONE BOYS! 🇮🇳🇮🇳🇮🇳

“Loop engineering” is a hot buzzphrase after mentions of it by Boris Cherny (Claude Code’s creator) and Peter Steinberger (OpenClaw's creator) went viral on social media. Loops are now a key part of how we get AI agents to iterate at length to build software. In this letter, I’d like to share my 3 key loops, shown in the image below, for building 0-to-1 products. These loops guide not just how I build software, but also how I decide what software to build. Agentic coding loop: Given a product specification and optionally a set of evals (that is, a dataset against which to measure performance), we can have an AI agent write code, test its work, and keep iterating until the code is bug-free and meets its specification. This idea of closing the loop took off around the end of last year, and it has been a game changer in enabling coding agents to work longer productively without human intervention. For example, over the weekend, I was building an app for my daughter to practice typing, and my coding agent could easily work for around an hour, using a web browser to check what it had built multiple times before getting back to me, without needing my intervention. The engineering loop executes quickly. Every few minutes, the coding agent might build and test a new version of the software. I hear frequently from developers who are finding new ways to engineer more effective engineering loops. This is an active area of invention! Developer feedback loop: In this loop, a developer examines the current product and steers the coding agent to improve it. Last year, a lot of developers (including me) were acting as the QA (quality assurance) function for our coding agents, manually finding bugs and then asking the agent to fix them. But with coding agents much more able to test their own code, the amount of time we need to spend on this function has decreased significantly. This allows us to make higher-level product decisions, such as what key features to offer, where the UI needs improvement, and so on. The developer-feedback loop operates over time intervals between tens of minutes and hours — that's how frequently a developer might review a product and give feedback. In the case of the typing app, I changed my mind a few times about the visual design, what cat costumes she can unlock as she learns (she loves cats), and the user flow for a grown-up to log in and steer the child's learning experience. When a developer has a clear vision for what to build, it is still a lot of work to translate that vision into a specification for a coding agent to implement. Further, after the developer has seen an implementation, they might update (or perhaps clarify) the spec to steer it toward what they want. If you find that the system repeatedly runs into certain problems, building a set of evals for the agent becomes useful. AI-native teams are increasingly using AI to help shape product direction, for example, automating the gathering and analysis of usage data, summarizing written and verbal customer feedback, or carrying out competitive analysis. However, for pretty much all the products I’m involved in, I see humans as having a significant context advantage over current AI systems — we know a lot more than the AI system about the users and the context the product has to operate in — and thus humans play a critical role. Many people describe this human contribution as “taste,” but I prefer to think of it as humans having a context advantage, since that gives us a clearer path to helping AI systems get better. This also speaks to why this step can’t be automated: So long as the human knows something the AI does not, human-in-the-loop is needed to to inject that knowledge into the system. External feedback loop: This includes a wide range of tactics like asking a few friends for feedback, launching to alpha testers, or putting the code into production with A/B testing. These tactics are usually slow, rarely taking less than hours and sometimes taking days or even weeks. This data informs the developer vision, which in turn continues to drive the detailed product spec, which in turn drives the coding agent. With coding agents speeding up software development, more engineers are starting to play a partial product management role. For many engineers who are growing into this role, the hardest part is shaping the product vision and striking a balance between building (bridging the gap between vision and spec) and getting user feedback to evolve the vision. It is important to do both! I will write more about how to do this in future posts, but for now, I find it encouraging that engineers are playing an expanded role (just as product managers and designers now do more engineering). [Original text: The Batch]

In the last few months of DMK rule before the Assembly elections, four amendments were carried out by the Government in the TN HR&CE Act, 1959 and in certain Rules under the Act. 1. Amendments in Section 35 to facilitate unbridled looting of temple funds (L.A. Bill 40 of 2025) 2. Amendments to Alienation of Immovable Properties of Religious Institutions Rules to facilitate chronic encroachers of temple lands (G.O. 478 dtd. 01.12.2025) 3. Amendment to Investments of Temple Funds Rules (G.O. 83 dtd. 17.02.2026) 4. Amendment to Fixation of Lease rents to properties of Hindu Religious Institutions (G.O. 29 dtd. 14.01.2026) The common thread in all the above four amendments made by DMK Govt is "facilitation of Temple Looting" 1. Amendment to Section 35 - Since it is an amendment to the Act - not yet valid since it has not been approved by Hon'ble Governor of Tamil Nadu. 2. Amendment to Alienation of Temple Properties Rules - Atrocious Anti -Temple move by Anti-Hindu DMK Govt - I will be challenging this soon. 3. Investment Rules - I challenged it in May 2026 - the new Government was gracious to accord sovereign guarantee to Temple Deposits made in TN Power Finance - an NBFC owned by TN Govt. This case will come up again in 4 weeks. 4. Amendment to Fixation of Lease Rent Rules - a set of botched up Rules conceived in a hurry by misfits under directions of DMK Govt - too many contradictions and violations. My challenge to this set of absurd Rules came up as a PIL today before Madras High Court. Hon'ble 1st Bench of the Madras High Court was pleased to issue notice to Government and @tnhrcedept today. My gratitude to Sr. Counsel Shri Sankaranarayanan Sir and advocate Shri B. Jagannath. I request Hon'ble Chief Minister @CMOTamilnadu and Hon'ble Minister for @tnhrcedept Shri @RameshOffcl to review these anti- Hindu and anti-Temple Amendments in the HR&CE Act & Rules made by DMK Government and withdraw/cancel them to safeguard our temples.

keyboard_arrow_left Previous keyboard_arrow_right Next

This not what the world expects from Bharat !! India created history by winning its first-ever gold medal at the World Rowing Cup in Lucerne, Switzerland. Indian Army rowers Lakshay and Ujjwal Kumar Singh achieved the historic feat in the lightweight men’s double sculls final. The Indian duo clocked 6:26.09 to finish ahead of Hong Kong and the Netherlands, clinching the gold medal.

A 15-year-old dream has come true today. I started a PhD with the dream of creating a system that chants any Sanskrit shloka perfectly. And here I am opening sourcing 𝐕𝐚𝐠𝐝𝐡𝐞𝐧𝐮 - 𝐀 𝐯ṛ𝐭𝐭𝐚 (𝐦𝐞𝐭𝐞𝐫) 𝐚𝐰𝐚𝐫𝐞 ś𝐥𝐨𝐤𝐚-𝐭𝐨-𝐜𝐡𝐚𝐧𝐭 𝐭𝐞𝐱𝐭-𝐭𝐨-𝐬𝐩𝐞𝐞𝐜𝐡 (TTS) 𝐬𝐲𝐬𝐭𝐞𝐦 𝐟𝐨𝐫 𝐒𝐚𝐧𝐬𝐤𝐫𝐢𝐭. This is the world's first vrutta-aware, open-source TTS for Sanskrit Chanting.

keyboard_arrow_left Previous keyboard_arrow_right Next

THE INSPIRING STORY OF THE MAN WHO BUILDS IN INDIA.. FOR THE WORLD 🇮🇳 From a small village in Thanjavur, Tamil Nadu — where his father worked as a court stenographer — to building a $8+ billion global tech empire without a single rupee of VC funding. Sridhar Vembu ji cracked IIT Madras, earned a PhD from Princeton, worked at Qualcomm... and then walked away from the American dream. He came back to India. Started Zoho (as AdventNet) with family & friends' savings in a small Chennai apartment. Bootstrapped it into a SaaS giant that competes with Microsoft, Google & Salesforce — serving 100+ million users worldwide. But the real inspiration? He moved operations to rural Tenkasi. Built offices in villages. Created Zoho University to train college dropouts and local talent. Proved world-class software can be built from mud roads and mango groves — not just Silicon Valley glass towers. A barefoot billionaire who lives simply, rejects flashy wealth, and invests in rural India. Padma Shri awardee. True patriot. Real role model. Sridhar Vembu ji reminds us: You don’t need to chase the West. Build where your roots are. Dream bigger. Stay humble. Impact deeper. Thank you for showing what's possible with conviction, patience & swadeshi spirit 🙏 You are an inspiration for us sir. I use @zoho products now and I must say, they are amazing. Happy Birthday @svembu ji !! Lots of love, #FI

keyboard_arrow_left Previous keyboard_arrow_right Next

YESSESSSSSSSS, THE BOYS DID IT!!!! 🇮🇳🥹 India Volleyball Team defeated Defending Champion Bahrain to win Bronze at AVC Men's Cup 2026 FIRST EVER MEDAL FOR INDIA, JUST WOW!! 🤩

Learning how Naval Ravikant reads books will permanently change the way you read:

"திமுக செய்ததையே தவெக செய்கிறது" - திருப்பரங்குன்றம் விவகாரத்தில் நடப்பது என்ன? பிபிசி தமிழில் வெளிவந்துள்ள கட்டுரை bbc.com/tamil/articles…

அதிமுக ஆட்சியில் ஸ்ரீரங்கத்தில் யாத்ரி நிவாஸ் கட்டியதில் மிகப் பெரிய ஊழல் செய்திருக்கிறார்கள். கோயில் நிலம் சட்ட விரோத பரிமாற்றம் - ஸ்ரீரங்கம், சமயபுரம் கோயில் நிதி ஆதாரங்ள் சட்ட விரோதமாக எடுக்கப்பட்டுள்ளன. இவற்றையும் விசாரிக்க ஆவண செய்யுங்கள் @RameshOffcl

Office of TVK Ramesh @TVKRameshOff

2 weeks ago

ஶ்ரீரங்கம் யாத்திரி நிவாஸ் பக்தர்கள் தங்கும் விடுதியில் பொதுமக்கள் தங்குவதற்கு போலி இணையதளங்கள் மூலம் நடைபெறும் மோசடி குறித்து மாண்புமிகு அறநிலையத்துறை அமைச்சர் @RameshOffcl அவர்கள் திருச்சி மாவட்ட காவல் ஆணையர் அவர்களிடம் அளித்த புகாரின் அடிப்படையில் வெளிமாநில நபர் கைது.

7 94 376 47K 9

ஶ்ரீரங்கம் யாத்திரி நிவாஸ் பக்தர்கள் தங்கும் விடுதியில் பொதுமக்கள் தங்குவதற்கு போலி இணையதளங்கள் மூலம் நடைபெறும் மோசடி குறித்து மாண்புமிகு அறநிலையத்துறை அமைச்சர் @RameshOffcl அவர்கள் திருச்சி மாவட்ட காவல் ஆணையர் அவர்களிடம் அளித்த புகாரின் அடிப்படையில் வெளிமாநில நபர் கைது.