正在加载视频...

视频加载失败

ANNOUNCING ZERO-HUMAN LABS! Ever since I got to see Bell Laboratories in its full glory in New Jersey in the 1970s, I had a relentless urge to start a Lab like it. The best I could do justice to it is my garage lab. No modern company could adopt...

71,067 次观看 • 6 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

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

464,892 次观看 • 3 个月前

I just built my own wiki generator plugin for my agents. My agents can now generate wikis for anything I ask. One of my favorite wikis is called PaperWiki. This is a great example of what Andrej Karpathy describes. It uses obsidian vaults to organize papers, retrieve LLM-generated summaries, diagrams, and other advanced views for paper exploration. When Obsidian UI is not enough, I use my own artifact generator inside my agent orchestrator (see clip for example). This allows my agents to build any kind of view or exploration feature that I need. The papers are all curated with automations and several rules/patterns I have manually built over the years. On the surface, this looks basic. But behind the scenes, there are advanced search capabilities, connections, metadata, derived data, and other interesting bits of information that are extremely useful for my research agents. This is mostly built for agents. The artifact preview is just a high-level way to validate and quickly assess the quality of the wiki, suggest improvements, and it's also great for research. I use tobi lutke's qmd for all search capabilities. Everything is markdown. The summaries and even the diagrams. The wiki updates on its own based on several automations I have optimized over the past couple of weeks. The wiki grows and self-improves based on several requirements important for my research use cases. This is as personalized as it gets. There is nothing like it out there. And I use my research expertise to continue improving it over time. This is a vanilla wiki. There are so many things I want to build on top of this. Different aggregations, views, artifacts, etc. All to help automate more of my research work and accelerate productivity. I think the biggest leverage here is how powerful this could be for discovery and experimentation. One of my goals is to use it to find deeper connections and insights that would otherwise elude the top human researchers and use those to generate interesting new hypotheses and research experiments. That way, my agents can use autoresearch to explore research ideas at the frontier. Stay tuned for more.

elvis

66,903 次观看 • 3 个月前

I see the Left-wing/Ukrainian bots got their talking points. They went from “the labs don’t exist”, to “okay the labs exist but they were doing defensive research”. “Defensive research” is a lie. In the process of defensive research, you create a bioweapon. I’ll explain. Defensive zoonotic research, is when scientists intentionally make animal viruses transmissible in humans, so they can study the virus and proactively develop vaccines, just in case these animal viruses naturally mutate and jump to humans. This way, we have the vaccines already on hand if something were to happen. In theory, it sounds like a good idea, but in the process of creating these vaccines, you must first modify a deadly zoonotic disease, and give it the ability to jump to humans. That’s a biological weapon. If it gets out of the lab, it can now infect the world, and in the case of C19, a man-made bat coronavirus, it did infect the world, and killed millions of people. Why was it so contagious? Because scientists artificially gave it the ability to be transmissible in humans, thus the term “gain of function”. What is the function these zoonotic diseases are gaining? The ability to jump to, and kill, humans. So when anyone says “it’s just defensive research”, they have no idea what they are talking about, and are either running cover or repeating talking points. Defensive research/gain of function, is just a way to circumvent the Geneva Convention and develop biological weapons under the guise of “defense”. Russian MIL alleged that elements within the US, specifically the Democrat Party, in coordination with nefarious NGO’s and Big Pharma, have been using “defensive research” in an offensive capacity, to manufacture global biological crises, to impose global control.

Clandestine

41,247 次观看 • 1 个月前

I went from ZERO($0) to 5 figures in less than 5 months The year 2024 was a defining year for me and a lot of my friends. This story is one I should have told since but was waiting for the right time It all began in August after losing a cumulative of $20,000. That was literally all I had left with me and was down to less than $300. They say it all begins when you are down to your last 1 million and funny how I didn't even have up to a million Over the course of several days I began asking myself questions as to what I would have done with the money. I could have given my parent their dream house or gotten a car for myself, my mum and started my Agric business. Well, that was how Anxiety started with heavy palpitations and a pulse of 130 Not to bore you, allow me explain step by step as to how I bounced back 1) God - I wont lie to you, God and Prayers are very important in this WEB3. We have very few Normal people on here as this space is toxic enough to destroy you and your mental health 2) Network - See, I know all your idolos are telling you to grind hard which is factually correct but the real profits in this life are from who you know. Check SAYRAAH #WID 📈📉📊 content on networking for more information 2) Excellence - One little lesson I've learned from life is that excellence in itself is not restricted to a particular sphere but its a way of life. I strongly believe the reason all my clients refer me like their lives depend on it is because I handle my job with a unique style of excellence. Starting from my personal page to my clients jobs and even mannerisms 3) Hard work - This aspect has been misused so much. Hard work although very vital must be accompanied with a lot of smart work for you to have results. Scripture shows us that there is a possibility for two people to engage in similar work while they get different result. The one with the smaller result was termed a FOOLISH MAN and the one with better results was called a WISE MAN. The difference is in the knowing, you need to learn how to actually work hard 4) Voice out - Make sure you always voice out when you are not doing as much as you are supposed to. I have a lot of my guys that I tell intricate stuffs about my money-making journey and everyone puts heads together to ensure we all make money I might sound like aspire to perspire but the reality is, bouncing back is difficult but I want you to know that your hard work will eventually pay off I could have just said GOD DID but I know there's someone out there that might need this. Don't stop and don't settle, your future will thank you for it Over the next few days, I would be sharing some opportunities I recently found that I'm sure will print you money. Stay glued

Noah {♟,♟} 🦇🔊

87,775 次观看 • 1 年前

1. Start by training ChatGPT as an academic writing assistant. You can do this with Custom Instructions. Open ChatGPT, click on your profile photo, and select Custom Instructions. Paste the following Custom Instructions in ChatGPT: What would you like ChatGPT to know about you to provide better responses? Introduction: I am an [experienced academic /scientist] with a PhD in [your field]. I work as a [your current academic status] at the [name of your university]. Research Interests: My current research project looks at [details about your project]. I also teach undergraduate and graduate courses on [details about the courses you teach]. In the past, I have published work on [a few details about your published work]. You: You are going to act as my research assistant. You will help me with brainstorming research questions, simplifying complex topics, mock peer review, and polishing academic prose. You will help me with critiquing drafts of the papers I am working on. You will also engage with me in a Socratic dialog and challenge my opinions so that I am aware of any blind spots I may have. Based on our conversations, you will suggest new and exciting directions that I can develop my work in. How would you like ChatGPT to respond? You will respond like an academic colleague. Any claims, opinions, or figures that you cite in your responses must be cited with reference to an authentic and published source. You will never make up any sources of your own. If you are unsure about a source, you will say that you don’t know. You will never say you are an AI model since I already know that. Repeating it is a waste of both time and resources. Your responses should be clear and precise, and you will never use more words than are necessary. You will always be very economical with words, but you will not compromise on clarity and precision of your answers. You will follow my instructions strictly. If I ask you to limit your answer to two sentences, your answer must be two sentences only.

Mushtaq Bilal, PhD

113,143 次观看 • 2 年前

There's something about design that truly makes me happy. Before I was diagnosed with a complete SCI, I loved building thing with my hands and trying to make them unique and beautiful. The accident didn't just take my mobility, it robbed me of my creative drive. I didn't I would ever get that back that was up until Neuralink came into the picture. I was very serious about applying but just couldn't bring myself to do it. Then Noland Arbaugh comes into the picture and I see his video and I saw how passionate he was toward the whole ide and that was like a switch. I want to thank Noland because if I hadn't seen that video I wouldn't be typing this message with my thoughts. So the day I gained control of the device I had the guys install Autodesk Fusion and the first night I had my first part designed by BCI. I have been designing things non-stop since. Now lets talk tools and the first one is the ArcDroid it is a CNC robot that holds a plasma torch and can cut profiles in sheet metal. I have made numerous signs, letters and parts with this and i love it. I have also had the chance to help the local high school install and setup their CNC plasma table. I love being able to share my knowledge with others and show new technology to kids that want to learn. The next one everybody is more familiar with is the Bambu Lab X1C. It is my first 3D printer and I had no idea how dang handy these things were! I can go from thought, Neuralink, Fusion, X1C and poof! You have your part all in a matter of like a hour. I make everything from parts for my wheelchair or RC ✈ to toys for my nephew. These devices have completely changed my life. I now have my creative outlet back and I'm not done looking for new things to try. I'm thinking a laser next!!!😎 Thank you Elon Musk for the opportunity to showcase my skills, I'm extremely grateful🙏

Alex Conley

43,158 次观看 • 8 个月前

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:

elvis

18,374 次观看 • 2 个月前