正在加载视频...

视频加载失败

Rate my setup 😌 Undergoing OriginTrail v10 tests while the little one is sleeping. Insane watching my agents grow shared memory from World Monitor insights. Every assertion with clear provenance, looping into recommended actions. A true decentralized intelligence in action!

34,026 次观看 • 2 个月前 •via X (Twitter)

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

V8 DKG Launches Now: A New Dawn for AI in 2025🌟 As 2024 draws to a close, we're excited to announce the immediate launch of V8 Decentralized Knowledge Graph (DKG)! This monumental release is set to redefine AI's capabilities as we step into 2025. What Does V8 Bring to the Table? 🧠Decentralized AI: AI agents can now leverage a 'collective memory' at internet scale, drawing from a shared, yet sovereign, knowledge base. This means AI can provide more contextual, coherent, and accurate interactions without compromising data integrity or privacy. 🚀Unmatched Scalability: With the capability to handle billions of Knowledge Assets, V8 DKG sets the stage for AI to grow and learn in ways we've only imagined, supporting everything from decentralized science to industry 4.0. 🔐Trust and Integrity: With integrated decentralized Retrieval Augmented Generation (dRAG), V8 DKG promotes AI that's more accurate, less biased, and inherently trustworthy. How to V8👇 To update your node from V6 to V8, delegate your TRAC utility tokens, and learn more about creating, connecting and owning your Knowledge Assets, make sure to thoroughly read the following documentation: 👉 With V8 DKG launch, you may now access the new: V8 Explorer👉 AND Staking Dashboard 👉 You may now also participate in V8 Staking Security Bounty by delegating new TRAC stake and report your findings. Read more: 👉 The V8 Staking Security Bounty will importantly contribute to the so-called tuning phase of V8 DKG launch (V8.0 to V8.1). Let's break records, as we usher in a new era of Internet Scale OriginTrail!

OriginTrail

561,195 次观看 • 1 年前

My baby is only 10 days old… born into famine and under fire My little boy… my innocent angel… Ali, not even ten days old, came into this world during one of the darkest and most brutal times. He was born in Gaza, born into a genocide. An infant with no fault except that he is Palestinian — born in a place where milk is under siege, childhood is a target, and dreams die before they’re born. His birth was a nightmare. His mother, exhausted from hunger and malnutrition, barely survived. She cannot breastfeed him… she barely has the strength to hold him. And my baby? He cries endlessly. No formula, no diapers, no crib to sleep in, no warmth, no safety — only the cold arms of war. One can of infant formula costs $100, and a pack of diapers is nearly $400 — and we need them every week at least. But I stand here empty-handed… powerless… broken. I cannot give my child the most basic of rights: to be fed, to be clean, to be held in peace. My son, forgive me… I never knew you would be born into a world so cruel. I never imagined your first taste of life would be hunger, deprivation, and pain. But I will never stop trying. To those reading these words — you are our hope. My children need the bare minimum to survive. Your donations, your compassion, your humanity — they are the only things that can save my baby from this slow death, from a hunger that is louder than war. Please… help me save Ali. Help me protect a childhood that began in tragedy.

Hema alsabea

41,916 次观看 • 1 年前

Dario Amodei just ended the debate about AI timelines with one number. Amodei: “Within 10 years we’ll get to what I call kind of country of geniuses in a data center. I’m at like 90% on that.” 90% confidence. From the CEO building it. Country of geniuses in server farms. 10 years. Not one smart model. Millions of expert-level agents operating simultaneously. Entire nation of genius intellect accessible in parallel. Amodei: “It’s hard to go much higher than 90% because the world is so unpredictable.” The 10% isn’t technology doubt. It’s whether civilization survives long enough to finish building it. Geopolitics. Infrastructure. Economic stability. Those are the risks. Not whether it works. World stays intact and intelligence explosion is inevitable. Not possible. Guaranteed. Critics argue about plateaus. Builders prepare for millions of concurrent genius agents. “Country of geniuses” is literal. Nation-scale exceptional intelligence, instant access, unlimited parallel queries. Not enhancement. Obliteration of intelligence as scarce resource. Every bottleneck from expert shortage disappears. Every knowledge problem becomes trivial through instant genius access. Amodei is certain about direction. Uncertain whether chaos disrupts completion. Not if. When. Single-digit years unless catastrophe intervenes. Not better tools coming. Intelligence stops being constraint for any cognitive work. Anthropic’s CEO is 90% sure this happens within a decade. Only question is global stability lasting long enough. When it arrives, every assumption about human advantage, expert value, knowledge work economics becomes obsolete instantly. Intelligence transitions from scarce expensive resource you hire to abundant free infrastructure you access. And that transition doesn’t negotiate. Doesn’t phase in gradually. Just renders the old model inoperable the moment adequate scale deploys. 10 years. 90% probability. Country of geniuses. The future isn’t uncertain. Just the path staying clear long enough to reach it.

Dustin

22,266 次观看 • 4 个月前

Making OpenCode as lean as Pi agent? Just trimmed 25k out of OpenCode's system prompt (from 30k to 4-5k tokens) How? Just disable skills and get rid of massive skill definition bloat. Who needs skills anyway? Just kidding, this is the not the way. It makes the agent lame and defeats the point of using one. But it sets a precedent: Find a way to use skills without their definitions pre-loaded into the system prompt every single turn. Another interesting stuff: Upon testing this temporary "no skill setup" with two of hottest OpenCode Zen free models, Mimo V2.5 vs DeepSeek V4 Flash: One thinks more and talks less One thinks less and talks more Check the video to see which is which If you made it here, I'm finding a way to leanest OpenCode setup that I can get I simply don't believe that OpenCode can't be as lean as Pi Upon tinkering, I made a plugin that temporarily extracts the system prompt while I test, and noticed the hundreds of definitions in it from my .agents/skills directory which is shared across all my coding agents (Cursor, Antigravity, Claude, etc.) Of course disabling skills is not the answer, but it just proved that there is a way to strip the system prompt of these massive skill defs Aside from the system prompt hierarchy that injects confusion imo if you have a conflicting and redundant AGENTS.md which I discovered upon digging into OpenCode's source code Apparently it has prompt.ts/system.ts/instruction.ts/llm.ts and loads base .txt prompts based on model family (claude/gpt-o/gpt-5/codex/gemini/others) that all work together to make OpenCode aware of who it was and how it should use tools and become a "coding agent" Gotta find the most minimal mix that fits right into my workflow Make OpenCode as lean as Pi? We'll see. All in

raymel 👋

37,196 次观看 • 1 个月前

HiveMind is a superintelligent network in which a central AI (MIND) orchestrates a swarm of uniquely coded Minds that drive mass data ingestion and limitless content creation. For decades, our approach has been to create content first, then analyze it into data afterwards to understand what worked. This was always backwards - analyzing the aftermath rather than engineering the success from the start. Traditional Flow: Content → Data Analysis → Insights Content isn't one-size-fits-all - a cooking show that captivates a senior audience on YouTube might bore a teenager who craves quick, dynamic experiences. The challenge isn't just creating content; it's creating the right content for the right audience. We need to change this. This is where HiveMind's specialized agents transform the landscape. Each agent, while connected to the central MIND, excels in its unique domain. One agent masters the art of children's educational content, while another crafts compelling cooking narratives. Another might specialize in rapid-fire social content that resonates with Gen Z. Through HiveMind, every piece of content generated becomes new data that teaches the system to create even better content. The system gets smarter with every cycle, understanding at an increasingly sophisticated level what makes content effective and engaging. But the true power lies in the feedback loop. Every interaction, every engagement, flows back to MIND, enabling each agent to evolve and refine its approach. This isn't just content creation - it's content evolution. As audiences engage, agents learn, adapt, and improve, making each new piece more effective than the last. In essence, we're not just building content creators; we're developing specialized digital artists who understand their audience intimately and grow smarter with every creation. You can think of it this way: Data → Pattern Recognition → Optimized Content → Engagement Data → Even Better Content Tzar

Tzar

26,190 次观看 • 1 年前

Building a personal knowledge base for my agents is increasingly where I spend my time these days. Like Andrej Karpathy, I also use Obsidian for my MD vaults. What's different in my approach is that I curate research papers on a daily basis and have actually tuned a Skill for months to find high-signal, relevant papers. I was reviewing and curating papers manually for some time, but now it's all automated as it has gotten so good at capturing what I consider the best of the best. There are so many papers these days, so this is a big deal. You all get to benefit from that with the papers I feature in my timeline and on DAIR.AI. The papers are indexed using tobi lutke qmd cli tool (all of it in markdown files along with useful metadata). So good for semantic search and surfacing insights, unlike anything out there. I am a visual person, so I then started to experiment with how to leverage this personal knowledge base of research papers inside my new interactive artifact generator (mcp tools inside my agent orchestrator system). The result is what you see in the clip. 100s of papers with all sorts of insights visualized. I keep track of research papers daily, so believe me when I tell you that this system is absolutely insane at surfacing insights. This is the result of months of tinkering on how to index research and leverage agent automations for wikification and robust documentation. But this is just the beginning. The visual artifact (which is interactive too) can be changed dynamically as I please. I can prompt my agent to throw any data at it. I can add different views to the data. Different interactions. I feel like this is the most personalized research system I have ever built and used, and it's not even close. The knowledge that the agents are able to surface from this basic setup is already extremely useful as I experiment with new agentic engineering concepts. I feel like this knowledge layer and the higher-level ones I am working on will allow me to maximize other automation tools like autoresearch. The research is only as good as the research questions. And the research questions are only as good as the insights the agents have access to. Where I am spending time now is on how to make this more actionable. I am obsessed about the search problem here. The automations, autoresearch, ralph research loop (I built one months ago) are easier to build but are only as good as what you feed them. Work in progress. More updates soon. Back to building.

elvis

464,070 次观看 • 3 个月前