deadphoenix

Places to meet a quality woman: < Gym. 9 AM. Weekend. No hangover. No excuses. She's already doing better than 90% of people. < Airports. Underrated as hell. People with direction. Not stuck, not lost. < Good grocery stores Whole Foods, farmer's markets.... You see what she eats, you see how she lives. < Nice cafes. Not the cheap, loud, chaotic ones. Calm places. Better crowd. Simple. < Parks or the beach. Sunny day. No pressure. No acting. Just real life. < Small bookstores. Not chains. If she's there, she can sit still and think. That's rare now. < Avoid church. I'm not explaining that one.

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

स्त्रियों को कटुवाक्य न बोलें, कष्ट न दें, फूल से भी न मारें। इन्हें पीड़ित करने वाले से देवगण विमुख हो जाते हैं। Do not speak harshly to women, do not cause them distress, do not strike them with even a flower. Devatā-s turn away from those who inflict suffering upon women.

How I understand AI evolving . let me explain it through building a house. Suppose you want to build a house. At the base, "LLM" ( perplexityAI, chatgpt, gemini, etc) is like an expert . You can ask anything about building a house, from design to materials to costs, and it gives all the answers. Then comes "Agentic ". Now this expert doesn’t just advise, it starts handling small tasks on its own, like creating basic designs, estimating costs, or scheduling work. Next is "Multi-agent" .. Its like a full team coming together: architect, engineer, contractor and each building different parts of the same house. Then comes "AGI" . One person who can design, plan, and build the entire house like a complete human expert. At the top is " SI " . A super intelligent mind that can predict future needs, optimize everything instantly, avoid mistakes before they happen, and build in ways humans haven’t even imagined yet. From answering… to doing….. to teamwork….. to mastery…... to beyond human. First you learn ….. then you earn… then you evolve. " Complex ideas. Simple words." ✌️

Vidura shares a litmus test for friendship.

If you get damaged physically, the whole world of doctors and people can cure you. But if you are damaged emotionally and mentally, then only a very wise man can cure you. And women damage men emotionally and mentally; they damage the man internally who doesn’t have wisdom, understanding, stillness, and detachment. If you are wise, with understanding and detachment, then there is no one who can damage, hurt, or harm you.

So your thought is just recycled data from the past. Thought is about survival, not for exploration or enlightenment because your thought is only a permutation and combination of what you already know – nothing new can happen. Only if you create a distance between what is you and what is your body and mind, can you experience something new. ##SadhguruWisdom

#RamaNavami #MaryadaPurushottam #SadhguruWisdom

समझदारी...

Gumroad’s test suite of 16,000 tests has been flaky for years. This slowed down shipping tremendously. This week, Gianfranco used @karpathy’s autoresearch and @steipete’s OpenClaw to stabilize our test suite overnight. And his code is open source, so you can (have your agent) do it too. (And our code is open source too so you can see every single fix on GitHub.)

Living an Exuberant Life is only possible when you are able to dance upon the uncertainties of life. #SadhguruQuotes

संसार की सभी नारियां दुर्गा जी के अंश से ही उत्पन्न हैं। यही देवी गृहस्थों को ऐश्वर्य देती हैं और घरों में गृहलक्ष्मी के रूप में रहती हैं। All women of world have originated from a fraction of Durgā Devi. She makes householders prosperous & resides in their homes as Gṛhalakṣmi

Amjad Masad, CEO of Replit: "I don't want my Tesla autopilot to be vibe-coded."

This just flipped EVERYTHING. The U.S. Federal Reserve is now NOT expected to cut rates until 2027. And get this: There’s now a 51% chance of a RATE HIKE. Yes — hikes are back on the table. What just happened? 👇🧵 1/

ओशो 🌻

DARK HOSPITAL DEATH FACTS 1. Nurses often say 3-4 a.m. is when most patients pass away - the body is at its weakest during those hours. 2. Some terminal patients suddenly get a burst of energy before death - they seem normal.. then pass within hours. 3. Hearing is believed to be the last sense to fade - which means patients may still hear loved ones even when unrespossive. 4. In rare cases, bodies can make small sounds after, death due to trapped air leaving the lungs - which can terrify new hospital staff. 5. Some hospice workers say certain patients 'know` the exact day they're going to die - and mentally prepare for it.

Beyond the Mind lies the Intellect, beyond Intellect the Soul, and beyond all — the Infinite Purusha. . #Nachiketa #KathaUpanishad #vedanta #AncientWisdom #VedicPhilosophy #InnerJourney

Relationships are not about compatibility, companionship, or seeking happiness from each other. They are an opportunity to create a Union that paves the way to a greater possibility. #SadhguruQuotes

On Sanyasa in 2026: 1. I am not comfortable recommending Sanyasa in today’s world. 2. The quality of Sanyasa today has been degrading sharply over last few decades. In many places, what survives is outer costume without inner yogyata. 3. The modern hyper-connected world has destroyed the conditions that once supported deep Sanyasa. Constant stimuli, constant access, constant interruption - this is not the ecology in which long solitude and severe Sadhana arise easily. 4. A true Sanyasi is meant to be a Yati - one in motion (Yatra), unattached, not rooted in permanent social identity or fixed residence. Today, many do not leave society. They merely shift from one social structure into another. That is not real detachment. 5. Many now enter Sanyasa not from mastery, but from exhaustion, confusion, heartbreak, failure, or inability to handle worldly life. That is escapism - palaayan, not Sanyasa. It harms both the individual and society. 6. Many also enter in emotional enthusiasm without sufficient conquest over senses, anger, Rajas, and Tamas. Later, cravings return. The result is damage to body, mind, and public trust. 7. Sanyasa demands a life of rigorous Swadhyaya, Tapa, and Ishwar Pranidhana. Veda Sadhana is not optional. Yet shockingly, many modern Sanyasis are functionally illiterate in the Vedas. Some know little beyond a few inherited slogans. Some even drift into intoxicants and delusions while speaking of enlightenment. 8. Unless a Sanyasi is rooted in Veda Sadhana and stretches his mental powers to the highest degree, he does injustice to himself, to society, and to the very idea of Sanyasa. The ancient texts do not permit dilution here. 9. Sanatan Dharma does not force one narrow path. The Vedic framework provides multiple valid routes to Eeshwar for different temperaments in different eras and situations. 10. For most people today, a better path is this: build Sattva, do Sewa, remain in Swadhyaya, and pursue disciplined Sadhana. 11. That path is safer, cleaner, and more practical for both self and society. That is what Krishna's Geeta essentially recommended to world via Arjuna. 12. In today’s world, Sanyasa should be treated as an exception for the truly exceptional - not as a refuge for those defeated by love, career, family, or the ordinary demands of life. 13. Unless a person has already demonstrated rare brilliance, deep discipline, and unusual adhikara, Sanyasa is usually the wrong recommendation. 14. For most serious seekers of Moksha today, Patanjali’s Yoga - especially Chapters 1 and 2 - offers a far more reliable framework than the degraded forms of Sanyasa now seen in many places. 15. If you are a young man or woman, unless you have some truly extraordinary god-gifted visible genius, Sanyasa is not for you, no matter what you have read or someone you admire says. Instead be in the world, use world as your toolkit to Moksha. If you achieve extraordinary geniuses later, reconsider then. Till then, postpone Sanyasa and do your duties with Ananda. 16. Extraordinary genius will not come via mere Dhyana or some Kundalini Jagaran etc. Such claims are against Vedas. Dhyana will definitely help. But you will need to do Tapasya - hard work - to achieve genius. Rama, Krishna - everyone worked hard to master their weapons. You simply do not have an exception. 17. In summary, Sanyasa is not for you, neither the best path for you, nor the aspirational path for you unless there is visible evidential genius to justify that. (Think of Adi Guru Shankaracharya - are you in that league? Have you never felt anger, lust, depression? Are you always in Aanand? Are you having way higher aptitude than others? etc etc) What is the proof? If not, be humble, be what you are and choose your best path.) 18. Today, we need warriors who can protect Sanyasa Dharma more than Sanyasa. Why not commit to countering unlawful conversions on Bhoomi as an alternate to modern easy Sanyasa? Why not work to protect innocent like Hanuman? Why not teach masses by example and proof on what Dharma means? Study Vedas. Judge yourself ruthlessly. And then take any step. Sanjeev Newar (Yes, there are still exceptional individuals and traditions that guard Sanyasa with rigor and choose candidates with real care. But they are few. This post is about the widespread deviation from strict Vedic maryada, not about those rare exceptions.)