Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

"Everyone's talking about continual learning. That's entirely where this space is going to go." The Applied Compute platform is architected around that premise: build memory and intuition from fragmented data across your entire org, train reasoning models directly on top of it, and close the loop. A model is... show more

Applied Compute

5,120 subscribers

64,309 Aufrufe • vor 5 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓

codila

23,915 Aufrufe • vor 20 Tagen

Hermes Agent just got an update nobody is talking about. And it replaced all my paid tools. It is now free forever. It runs a local model called North Mini Code. You can build games like Skyrim or Matrix stuff fast. It is simple and runs on our Agent OS system. Get clear steps and real results today. Comment Agent OS to get the full free guide sent to you right now.

Hermes Agent just got an update nobody is talking about. And it replaced all my paid tools. It is now free forever. It runs a local model called North Mini Code. You can build games like Skyrim or Matrix stuff fast. It is simple and runs on our Agent OS system. Get clear steps and real results today. Comment Agent OS to get the full free guide sent to you right now.

Julian Goldie SEO

10,554 Aufrufe • vor 1 Monat

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

Rohan Paul

120,488 Aufrufe • vor 1 Monat

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

GREG ISENBERG

376,293 Aufrufe • vor 4 Monaten

$WDC CEO says storage demand and requirement compound and grow whether AI runs on US frontier models or cheaper open-source ones. "Whether it's the traditional frontier models that you've seen in the U.S. that are premium-based, or some of the new open-source, more economical models, the underlying requirement is still that they're going to require a lot of data to support the training of these models." "These models are going to generate a lot more data that requires storage for us." "So we view it as very positive, because even as compute maybe drives greater efficiency in terms of compute and memory resources, the requirement for storage is just going to compound and grow." "So we view it very positively for demand going forward."

$WDC CEO says storage demand and requirement compound and grow whether AI runs on US frontier models or cheaper open-source ones. "Whether it's the traditional frontier models that you've seen in the U.S. that are premium-based, or some of the new open-source, more economical models, the underlying requirement is still that they're going to require a lot of data to support the training of these models." "These models are going to generate a lot more data that requires storage for us." "So we view it as very positive, because even as compute maybe drives greater efficiency in terms of compute and memory resources, the requirement for storage is just going to compound and grow." "So we view it very positively for demand going forward."

Fireside Alpha

11,921 Aufrufe • vor 5 Tagen

The government is failing on cancer waiting times, just as it has failed on the economy and on asylum. Labour has a mission to build an NHS that is fit for the future, where patients are treated on time again and where fewer lives are lost to cancer.

The government is failing on cancer waiting times, just as it has failed on the economy and on asylum. Labour has a mission to build an NHS that is fit for the future, where patients are treated on time again and where fewer lives are lost to cancer.

Keir Starmer

209,214 Aufrufe • vor 3 Jahren

Most AI tools today are just command-takers. You type, it responds. You click, it executes. There's truly no learning, no memory, no adaptation. You're still doing most of the work. Which is why Miles by Avo on Solana would make so much sense if built well. From what I understand so far, miles learns about you over time, adapts to how you operate, and figures out the tools you struggle to navigate on your own. Less clicking, more conversation, the more you use it, the better it gets at working with you, not just for you. That shift from command-follower to learning companion is bigger than it sounds. It's the difference between a tool and an agent that actually knows you. The second one is Agent Grid and this one is for builders and power users. But as I mentioned in this video, I'm still studying the Agent Grid. I'd come talk about it once I learn properly about it. Souren just keeps shipping!

Most AI tools today are just command-takers. You type, it responds. You click, it executes. There's truly no learning, no memory, no adaptation. You're still doing most of the work. Which is why Miles by Avo on Solana would make so much sense if built well. From what I understand so far, miles learns about you over time, adapts to how you operate, and figures out the tools you struggle to navigate on your own. Less clicking, more conversation, the more you use it, the better it gets at working with you, not just for you. That shift from command-follower to learning companion is bigger than it sounds. It's the difference between a tool and an agent that actually knows you. The second one is Agent Grid and this one is for builders and power users. But as I mentioned in this video, I'm still studying the Agent Grid. I'd come talk about it once I learn properly about it. Souren just keeps shipping!

Sir Khaycee

20,419 Aufrufe • vor 4 Monaten

Hermes agent just left the terminal. 𝗛𝗲𝗿𝗺𝗲𝘀 𝗗𝗲𝘀𝗸𝘁𝗼𝗽 dropped yesterday. native app for macOS, Windows, and Linux. for months Hermes was the agent that learned your projects, wrote its own skills, and built a model of who you are. all of it buried in terminal logs. now it has a window. the important part is that it's not a wrapper. it runs the same agent core, the same sessions, memory, and skills as the CLI. you can start a task in the terminal and finish it in the app without anything resetting. the state is shared across every interface, not copied between them. what the GUI actually adds: → streaming chat that shows live tool calls and inline reasoning instead of a spinner → a preview rail that renders pages, code, and images right beside the conversation → an artifacts panel that collects every file the agent has ever produced → remote gateway mode, so you can point the app at a VPS and run the heavy work elsewhere → skills, cron, profiles, and gateways managed point-and-click instead of through YAML → voice mode, drag-drop files, and inline image generation remote gateway mode is the one worth slowing down on. the agent runs 24/7 on a $5 server while you control it from your laptop like a local app. other agent UIs are chatboxes with a logo. this one shows the autonomy instead of hiding it, so you watch the skills load, the tools fire, and the artifacts pile up as it works. it was teased in Jensen's GTC keynote. MIT licensed, local-first, no telemetry. if you already run Hermes, download it and everything is already there. your chats, memory, and skills carry straight over. i wrote a full masterclass on Hermes Agent that walks through the SOUL. md identity layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents 24/7. desktop is the interface that finally does all of it justice. the article is quoted below.

Akshay 🚀

51,474 Aufrufe • vor 2 Monaten

The biggest marketplace on Earth won't be the assets humans own. It'll be the data AI needs. Everything that can be digitised is getting pulled in to train the next models. Every scientific dataset, every piece of research sitting in a university, every sensor reading off every John Deere tractor in a field. All of it feeds the machine, and almost none of it is visible to us. What comes out is an agentic economy running at machine speed. You plug your data into a vault, and agents monetise it on your behalf, trading with other agents in real time, in a marketplace we never see. The company sitting on proprietary data becomes part of it without even knowing. This is what the Economic Singularity actually looks like from the inside. The real economy stops being the one we can see and price, and moves somewhere we can't follow. You own a piece of it, or you get priced out of it. Jordi Visser.

The biggest marketplace on Earth won't be the assets humans own. It'll be the data AI needs. Everything that can be digitised is getting pulled in to train the next models. Every scientific dataset, every piece of research sitting in a university, every sensor reading off every John Deere tractor in a field. All of it feeds the machine, and almost none of it is visible to us. What comes out is an agentic economy running at machine speed. You plug your data into a vault, and agents monetise it on your behalf, trading with other agents in real time, in a marketplace we never see. The company sitting on proprietary data becomes part of it without even knowing. This is what the Economic Singularity actually looks like from the inside. The real economy stops being the one we can see and price, and moves somewhere we can't follow. You own a piece of it, or you get priced out of it. Jordi Visser.

Raoul Pal

78,736 Aufrufe • vor 18 Tagen

quants don't predict markets. they stopped trying years ago retail is still asking "where is price going?" - quants switched to a different question entirely "given the current state, what's the probability distribution of outcomes" that's not a semantics game. it changes the math entirely stochastic processes model how a system evolves probabilistically - not picking a direction, mapping where each path leads and how likely it is ornstein-uhlenbeck does this for mean reversion: drift rate back to equilibrium, variance around that path same price data everybody has. different equation math is a century old, free in every applied probability textbook Bookmark and learn this before it gone you've been drawing trend lines while they ran probability distributions on same numbers it was never about data it was the question you were taught to ask

quants don't predict markets. they stopped trying years ago retail is still asking "where is price going?" - quants switched to a different question entirely "given the current state, what's the probability distribution of outcomes" that's not a semantics game. it changes the math entirely stochastic processes model how a system evolves probabilistically - not picking a direction, mapping where each path leads and how likely it is ornstein-uhlenbeck does this for mean reversion: drift rate back to equilibrium, variance around that path same price data everybody has. different equation math is a century old, free in every applied probability textbook Bookmark and learn this before it gone you've been drawing trend lines while they ran probability distributions on same numbers it was never about data it was the question you were taught to ask

Livsun

13,315 Aufrufe • vor 2 Monaten

The Father of HBM, Kim Jung-ho says physical AI is really a memory problem, because a self-driving car can't react faster than its memory can recall what it learned, and the stakes are: it cannot be a second late on the brakes. "Physical AI is memory AI." "The car crashes as it drives, remembers it all, and learns from it." "What's harder is the learning and reasoning must be real-time. A self-driving car can't hit the brakes a second late." "So here not just capacity, but speed matters too. Memory's speed." "Future memory will lead the AI revolution, and there it's speed and capacity. Speed is bandwidth, capacity is stacking. That's how I see it." ______ More from his lecture here:

The Father of HBM, Kim Jung-ho says physical AI is really a memory problem, because a self-driving car can't react faster than its memory can recall what it learned, and the stakes are: it cannot be a second late on the brakes. "Physical AI is memory AI." "The car crashes as it drives, remembers it all, and learns from it." "What's harder is the learning and reasoning must be real-time. A self-driving car can't hit the brakes a second late." "So here not just capacity, but speed matters too. Memory's speed." "Future memory will lead the AI revolution, and there it's speed and capacity. Speed is bandwidth, capacity is stacking. That's how I see it." ______ More from his lecture here:

Fireside Alpha

28,362 Aufrufe • vor 5 Tagen

Did you know that Facebook made $134.9 billion in 2023 from selling your data? Our society has come to the point where we accepted an unfair model in which privacy is being exploited and data gifted to big tech that is selling it for billions. We intend to break the norm of how data is shared on the internet because it is outdated and unfair. You should be empowered with more control and monetization models for your data!

Did you know that Facebook made $134.9 billion in 2023 from selling your data? Our society has come to the point where we accepted an unfair model in which privacy is being exploited and data gifted to big tech that is selling it for billions. We intend to break the norm of how data is shared on the internet because it is outdated and unfair. You should be empowered with more control and monetization models for your data!

Solana ID 🪷

30,457 Aufrufe • vor 1 Jahr

$PLTR is one of the cleanest ways to play the AI cycle because it benefits from the entire infrastructure buildout without financing the data centers, chips, memory, power or networking underneath it. Palantir is also emerging as one of the biggest sovereign AI winners by building the control layer that determines what AI understands, which proprietary data it can access and what decisions or actions it can influence inside an organization. OpenAI and Anthropic create the intelligence while Palantir connects it to permissions, workflows and real operating systems where measurable economic value is produced.

$PLTR is one of the cleanest ways to play the AI cycle because it benefits from the entire infrastructure buildout without financing the data centers, chips, memory, power or networking underneath it. Palantir is also emerging as one of the biggest sovereign AI winners by building the control layer that determines what AI understands, which proprietary data it can access and what decisions or actions it can influence inside an organization. OpenAI and Anthropic create the intelligence while Palantir connects it to permissions, workflows and real operating systems where measurable economic value is produced.

Shay Boloor

198,127 Aufrufe • vor 6 Tagen

Enterprise AI deployments today are frozen in time. Model capabilities stagnate in production. The problem compounds because companies aren’t static either. Every time your company improves, the model falls further behind. The bottleneck is continual learning. How does a model do something once and improve from feedback? The future of enterprise AI is Specific Intelligence: custom models teams own, trained on a company’s choices, interaction by interaction, using internal knowledge general models cannot access. Applied Compute helps companies train, serve, own, and improve custom models. Thanks Apoorv Agrawal for having Yash Patil at MS&E 435 to talk about the future of model training.

Enterprise AI deployments today are frozen in time. Model capabilities stagnate in production. The problem compounds because companies aren’t static either. Every time your company improves, the model falls further behind. The bottleneck is continual learning. How does a model do something once and improve from feedback? The future of enterprise AI is Specific Intelligence: custom models teams own, trained on a company’s choices, interaction by interaction, using internal knowledge general models cannot access. Applied Compute helps companies train, serve, own, and improve custom models. Thanks Apoorv Agrawal for having Yash Patil at MS&E 435 to talk about the future of model training.

Applied Compute

12,751 Aufrufe • vor 2 Monaten

People have this purist notion that kids should just be self-motivated to do well. For about 5% of them, that's true. But what about every other kid? Motivation is 90% of learning. Our guides figure out what motivates each kid and use it to get them to put in the work. Over time that builds a confidence anchor: the one win where a kid did something hard and hit their goal. Confidence in yourself might be the most valuable thing a kid can build. It changes your entire academic path. And yes, sometimes it starts with an Amazon cart.

People have this purist notion that kids should just be self-motivated to do well. For about 5% of them, that's true. But what about every other kid? Motivation is 90% of learning. Our guides figure out what motivates each kid and use it to get them to put in the work. Over time that builds a confidence anchor: the one win where a kid did something hard and hit their goal. Confidence in yourself might be the most valuable thing a kid can build. It changes your entire academic path. And yes, sometimes it starts with an Amazon cart.

MacKenzie Price

64,069 Aufrufe • vor 1 Monat

Your data is your edge, but only if your AI is built on it. Rent a generic model and so can your competitor. The companies with an edge are deploying custom models that they own and improve over time. Our co-founder Rhythm Garg recently stopped by South Park Commons to share how companies are owning their intelligence with Applied Compute.

Your data is your edge, but only if your AI is built on it. Rent a generic model and so can your competitor. The companies with an edge are deploying custom models that they own and improve over time. Our co-founder Rhythm Garg recently stopped by South Park Commons to share how companies are owning their intelligence with Applied Compute.

Applied Compute

118,922 Aufrufe • vor 2 Monaten

I’m worried that the US government debt problem will get so bad that the US will “go broke” and I believe that there are steps we can take to prevent it. I am in the process of completing a comprehensive study about the mechanics of how countries go broke, where the US government is in its Big Debt Cycle, and what policymakers and investors should do about it. The study will be published later this year as a new book: How Countries Go Broke: Principles for Navigating the Big Debt Cycle, Where We Are Headed, and What We Should Do. As with my prior books, I am going to pass along parts of it for free as I am writing, and I'd like to discuss what it says with you and others on social media. You can read Part One here:

I’m worried that the US government debt problem will get so bad that the US will “go broke” and I believe that there are steps we can take to prevent it. I am in the process of completing a comprehensive study about the mechanics of how countries go broke, where the US government is in its Big Debt Cycle, and what policymakers and investors should do about it. The study will be published later this year as a new book: How Countries Go Broke: Principles for Navigating the Big Debt Cycle, Where We Are Headed, and What We Should Do. As with my prior books, I am going to pass along parts of it for free as I am writing, and I'd like to discuss what it says with you and others on social media. You can read Part One here:

Ray Dalio

286,264 Aufrufe • vor 1 Jahr

Demis Hassabis confirmed every frontier AI lab is working on recursive self-improvement and in the same sentence said the safety risk of removing humans from the loop entirely keeps him up at night. That combination should stop you. The CEO of Google DeepMind just confirmed that the thing most people treat as a theoretical future risk is already the active focus of every serious lab on earth right now. He explained why it works in coding and math. The feedback loop is fast. You can verify whether an answer is correct almost instantly. You can generate synthetic training data from it. The loop closes quickly and cleanly. Then he said where it breaks down. In biology, chemistry and physics. Any domain where verifying a hypothesis requires a physical experiment in the real world. The loop does not close in seconds. It closes in weeks or months. Geoffrey Hinton said in his Nobel lecture that recursive self-improvement is the development he fears most and that once started it may not be possible to stop. Hassabis is not pushing back on that. He is describing the guardrails labs are building around a process they are already running. Every lab has to think carefully about the safety of a process where no human is in the loop. He said that as a constraint they are navigating right now. The question they are sitting with is how much of it to let run without a human watching. (Watch the full interview on YouTube at Two Minute Papers channel)

Demis Hassabis confirmed every frontier AI lab is working on recursive self-improvement and in the same sentence said the safety risk of removing humans from the loop entirely keeps him up at night. That combination should stop you. The CEO of Google DeepMind just confirmed that the thing most people treat as a theoretical future risk is already the active focus of every serious lab on earth right now. He explained why it works in coding and math. The feedback loop is fast. You can verify whether an answer is correct almost instantly. You can generate synthetic training data from it. The loop closes quickly and cleanly. Then he said where it breaks down. In biology, chemistry and physics. Any domain where verifying a hypothesis requires a physical experiment in the real world. The loop does not close in seconds. It closes in weeks or months. Geoffrey Hinton said in his Nobel lecture that recursive self-improvement is the development he fears most and that once started it may not be possible to stop. Hassabis is not pushing back on that. He is describing the guardrails labs are building around a process they are already running. Every lab has to think carefully about the safety of a process where no human is in the loop. He said that as a constraint they are navigating right now. The question they are sitting with is how much of it to let run without a human watching. (Watch the full interview on YouTube at Two Minute Papers channel)

Ihtesham Ali

68,231 Aufrufe • vor 1 Monat

Whoever is behind the CitizenApp which was launched yesterday has done a brilliant and fantastic job. The App is broad. It has a special feature known as CADIS(CitizenApp Data Interoperability System) where individuals databases are made available to institutions/agencies enrolled on the App without having to go through the stress of providing same information over and over. Again, it saves one from going to offices of agencies and going to waste productive hours just for their services. All you need is to do is just download the app and log in with your Ghana Card. It’s a one time sign up. Interestingly it has the features of which is a payment platform for government businesses. So you can buy ECG credits in the comfort of your home. The likes of SSNIT, ECG, NSS, GRA, Ghana Police, Ghana water Company, MMDAs and many others are all on the system. One can request his SSNIT statements on the same App. Trust me, Dr Bawumia is really speeding with this digitalization thing. Enjoy the video

Whoever is behind the CitizenApp which was launched yesterday has done a brilliant and fantastic job. The App is broad. It has a special feature known as CADIS(CitizenApp Data Interoperability System) where individuals databases are made available to institutions/agencies enrolled on the App without having to go through the stress of providing same information over and over. Again, it saves one from going to offices of agencies and going to waste productive hours just for their services. All you need is to do is just download the app and log in with your Ghana Card. It’s a one time sign up. Interestingly it has the features of which is a payment platform for government businesses. So you can buy ECG credits in the comfort of your home. The likes of SSNIT, ECG, NSS, GRA, Ghana Police, Ghana water Company, MMDAs and many others are all on the system. One can request his SSNIT statements on the same App. Trust me, Dr Bawumia is really speeding with this digitalization thing. Enjoy the video

Mr Irish

23,018 Aufrufe • vor 1 Jahr