Loading video...

Video Failed to Load

Go Home

Wow! This Changes Everything We Thought We Knew About Memory It is a groundbreaking big deal. TOU ARE MAKING GENERATIONAL MEMORIES RIGHT NOW IN EACH CELL! Scientists just found that your brain doesn’t just store memories — it stores the rules for how those memories will change in the...

42,636 views • 5 days ago •via X (Twitter)

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

Andrew Ng

131,850 views • 1 year ago

Love and Deepspace | New 5-Star Interactive Memory📼 [Sylus: Valleydream Bloom] The ancient remains have become a cradle for new life, just like the flower-covered valleys in the book. The stories of dragons, songs hummed on the breeze… In front of the lens, he grants your every wish, one by one. "Then this dragon will wait every night longing for the wind and petals to arrive." 📼Spring and Flowers Event Duration: 05:00, Apr. 30 - 04:59, May 18 (Server Time) You can select three out of the five event-limited 5-Star Memories: [Xavier: Inflorescence Imprints], [Zayne: Fragrant Possession], [Rafayel: Wisteria Waltz], [Sylus: Valleydream Bloom], and [Caleb: Floating Floraletter]. The drop rate of the 3 Memories you selected will be significantly increased. Each time you obtain a 5-Star Memory, there's a 75% chance it will be one of the three Memories you selected. *Notes: 1. During the event, you can change your selected Memories at any time. If you obtain a 5-Star Memory in a wish, there's a 25% chance that it will be an unselected Memory or a permanent 5-Star Memory. 2. After the event ends, the five event-limited Memories will not be obtainable through other means and will not enter the permanent Wish Pool: Xspace Echo. 3. The Wish event features Precise Wish and a pity system. You can check more details in upcoming event announcements. 📼Cumulative Wish Rewards During the event, after making a certain number of Wishes, you can claim rewards: Universal Headwear [Overbloom], [Deepspace Wish: Limited*20], His [Memory-Themed Outfits], selectable [Event-Limited 5-Star Memory] and more. *The cumulative rewards are only available during this wish event. 📼Limited-Time Memory Growth Bonus During the event, by completing the growth tasks of the event-limited 5-Star Memories, you can claim various Upgrade and Ascension Materials. When the event-limited Memories reach Rank 1, you can claim the [Special-Colored Memory-Themed Outfit] for the corresponding love interest. #LoveandDeepspace #SpringandFlowers #Sylus

Love and Deepspace

882,556 views • 1 year ago

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

200,950 views • 1 year ago

"The world falls, we fall together." Trailer of New 5-Star Memory Series [Tomorrow's Catch-22] Released! 💫Follow Love and Deepspace and Repost for a chance to win $50 (5 winners)! ⚠️Event Duration: 5:00 AM, Feb. 10 - 4:59 AM, Feb. 27 (Server Time) You can select three out of the five event-limited 5-Star Memories, [Xavier: Deluded Fiction], [Zayne: Immediate Disorder], [Rafayel: Extreme Dose], [Sylus: Innocent Birdcage], and [Caleb: Tainted Cuts]. The drop rate of the 3 Memories you selected will be significantly increased. If you obtain a 5-Star Memory in a wish, there's a 75% chance it will be one of the 3 Memories you selected. *Tips: 1. During the event, you can change your selected Memories at any time. If you obtain a 5-Star Memory in a wish, there's a 25% chance that it will be an unselected Memory or a permanent 5-Star Memory. 2. After the event ends, the five event-limited Memories will not be obtainable through other means and will not enter the permanent Wish Pool: Xspace Echo. 3. The wish event features the Precise Wish and a pity system. You can check more details in upcoming event announcements. ⚠️Limited Gift: Cumulative Wish Rewards During the event, after making a certain number of Wishes, you can claim various rewards: Universal Facial [Silverblade Rhapsody], [Deepspace Wish: Limited ×20], His [Memory-Themed Outfits], Limited Gift [Memory-Themed Hairstyle], and selectable Event-Limited 5-Star Memory. *The cumulative rewards are only available during this Wish event. ⚠️Limited-Time Memory Growth Bonus During the event, you can claim various Upgrade and Ascension Materials by completing the growth tasks. When the event-limited Memories reach Rank 1, you can claim the [Special-Colored Memory-Themed Outfit] for the corresponding love interest. ⚠️Special: Memory-Themed Outfit Bonus Each Original or Special-Colored Outfit Set includes a Memory-Themed Outfit and Facial. All can be used separately. *More content will be released with the version update. Please stay tuned! #LoveandDeepspace

Love and Deepspace

7,380,194 views • 1 year ago

The creator of High Bandwidth Memory (HBM) put a number on the AI build that should stop every infra investor cold. A cluster of a million GPUs runs at roughly 10-20% utilization (Save this). Kim Jung-ho spent thirty years building what feeds the GPU, and his claim is that the GPU is barely working. Here is what is actually happening. Every time a model generates output, the data has to be read out of memory, computed, and written back. The read and the write swallow almost the entire cycle. While that data moves, the GPU does nothing. It sits there, fully powered, fully paid for, waiting. By Kim's estimate the memory is doing only about 30 percent of the work it needs to do. The processor idles the rest. So a million installed GPUs run at 10 to 20 percent. You are not compute constrained. You are memory constrained, and the expensive part is standing around. Adding more GPUs does not fix this. It gives you more processors starving for the same data. Here is the part that decides the next decade. Memory can grow. When a cell cannot shrink any further, you stack it into a high-rise, layer on layer. A GPU cannot be stacked. It runs too hot and needs a cooler bolted to its back, so the one move that rescues memory is closed to the processor. The thing that can keep stacking compounds. The thing that cannot plateaus. The marginal dollar in an AI build now buys more by fixing the memory path than by bolting on another idle GPU. Which is why the companies that control memory bandwidth and supply are not suppliers to the AI trade. They are the AI trade.

Fireside Alpha

38,370 views • 1 month ago

Love and Deepspace | New Interactive 5-Star Memory❣️ [Caleb: Clearday Return] 🪐Official Discord: The agony of testing the medicine pierces to the bone, yet Caleb rescues you from the depths of suffering. It is said that Master Caleb plays a bone flute and poisons enemies from a thousand miles away. Whether his heart is poison or a cure, only those who keep stirring it can know. "And you never look guilty when you lie to me. Come. Let's go home." ❣️Mortality's Tenderness Event Duration: From 05:00 on Feb. 10 to 04:59 on Feb. 27 (Server Time) You can select three out of the five event-limited 5-Star Memories: [Xavier: Blades with Blossoms], [Zayne: Entwined Kites], [Rafayel: Carved Gemheart], [Sylus: Shared Lanterns], and [Caleb: Clearday Return]. The drop rate of the 3 Memories you selected will be significantly increased. Each time you obtain a 5-Star Memory, there's a 75% chance it will be one of the three Memories you selected. *Notes: 1. During the event, you can change your selected Memories at any time. If you obtain a 5-Star Memory in a wish, there's a 25% chance that it will be an unselected Memory or a permanent 5-Star Memory. 2. After the event ends, the five event-limited Memories will not be obtainable through other means and will not enter the permanent Wish Pool: Xspace Echo. 3. The Wish event features Precise Wish and a pity system. For more details, please check the in-game rule page. ❣️Limited Gift: Cumulative Wish Rewards During the event, after making a certain number of Wishes, you can claim various rewards: Universal Headwear [Gilded Trace], Deepspace Wish: Limited*20, His [Memory-Themed Outfits], Limited Gift [Memory-Themed Hairstyle], selectable [Event-Limited 5-Star Memory], and more. *The cumulative rewards are only available during this wish event. ❣️Limited-Time Memory Growth Bonus During the event, by completing the growth tasks of the event-limited 5-Star Memories, you can claim various Upgrade and Ascension Materials. When the event-limited Memories reach Rank 1, you can claim the [Special-Colored Memory-Themed Outfit] for the corresponding love interest. ——— 🪐Download and Log in Now: #LoveandDeepspace #MortalitysTenderness #Caleb

Love and Deepspace

369,209 views • 6 months ago

Micron is going to $4,000 and once you understand what inference actually is, the number stops sounding crazy (Save this). Dylan Patel just said that by 2030, OpenAI and Anthropic alone will need over 100 gigawatts of compute combined and by 2040, we may not even be measuring AI infrastructure in gigawatts anymore. We may be talking about terawatts. Every single one of those gigawatts needs memory to function. Without it, the compute is worthless. Most people heard that and thought about Nvidia but they should be thinking about Micron. Every AI model generating a response has two phases. The first is prefill, processing your prompt which is compute-heavy and the second is decode generating each word one token at a time and that phase is almost entirely memory-bound, not compute-bound. During decode, the GPU's processing units sit idle more than 95% of the time, waiting for data to arrive from memory. Google confirmed it in a research paper that decode-phase bottlenecks are dominated by memory bandwidth and capacity not raw compute. The GPU is not the bottleneck but the memory feeding the GPU is. This matters because inference is now where all the money lives. Training a model happens once, Inference happens billions of times a day every ChatGPT response, every Claude output, every agentic workflow running in the background and every one of those token streams is a billing event tied directly to memory performance. Adding more GPUs does not fix this because GPUs are already underutilized in inference because they are sitting idle waiting on memory. Adding more memory bandwidth and capacity is what directly reduces token cost, reduces latency, and allows the same cluster to serve dramatically more users simultaneously. Longer context windows compound the problem further, a model running a 1 million token context window requires dramatically more memory per session than a 10,000 token window, and every new model generation pushes context longer. The market treats memory as a downstream beneficiary of Nvidia orders. The correct framework is the opposite, Micron is the upstream constraint on how much value every Nvidia GPU can actually generate at inference scale. Micron guided Q4 to $50 billion in revenue, has HBM4 ramping at twice the pace of the prior generation, and CEO Sanjay Mehrotra has said supply will not catch demand before the end of 2027. At 8x forward earnings on $112 projected FY2027 EPS, Micron is the most undervalued infrastructure company in the entire AI stack. Inference is memory. Memory is Micron and the inference ramp has barely started. Milk Road Pro members are already up massively on this position and we're just getting started. If you want the full breakdown of what we're buying and why, come join us for just a dollar using the link below!

Milk Road AI

128,678 views • 1 month ago

Happy to properly launch Anna, the proactive AI agent for parents! Uncovering a bit of the technology behind the scenes! Building Anna is where I learned: 💾 Memory as plain text sucks. You need structured memory. Like a full-blown PostgreSQL DB that stores your tasks and calendar in a structured manner. Most harnesses are good at coding-related stuff. Let it do the query. Don't let it vibe-search the memory. Let it vibe your SQL query 💭 Dreaming is a useful concept for enhancing memory to feed the LLM context. But DO NOT vibe your dream. Asking your agent to "hey, just dream and keep the relevant memory around" is a recipe for deleting a bunch of important information and keeping trash around. Your dream needs to have some Taxonomy (or better, Ontology). What information is important? For who? With what object? What can they do? And again, these are impossible to describe and act well without a proper schema 🔄 Loop Engineering is important for smoothing out rough edges in the system we build. But even expensive loop engineering with a state-of-the-art model can't out-engineer bad system design. The highest leverage an AI Engineer can do is actually building the right system design, and having an eye on both product delight and engineering scalability There are several more insights that I plan to cover in a dedicated video about Agentic AI Engineering. But it's actually a huge relief that the future of software engineering... is still software engineering

Gogo | Dota for Toxicity

30,766 views • 1 month ago

Have you ever seen how DNA is organized? It's astounding. A single strand of your DNA, when stretched out, is ~2 meters, or ~6.5 feet long. If you stretched out all the DNA in your body end to end, it could cross the entire solar system, from the sun to Pluto, 17 times. You could wrap all your DNA around the Earth like a rubber band ball almost 2 million times. The storage capacity of DNA is so high that all the world’s digital data (estimated around 175 zettabytes by 2025) could theoretically be stored in just 178lbs of DNA. Imagine, one single server that could handle the entire world's annual data needs. And yet, all of this fits inside the nucleus of a cell, invisible to the naked eye. How is that even possible? To prevent DNA from becoming an tangled mess, unusable for anything, it is organized and packed very specifically. If not for this organization, DNA would be completely unusable for any of Life's processes. It would clump together, unable to be pulled apart to be read by the many interacting molecular systems. To start, smaller segments of DNA are coiled tightly around a special protein called a Histone, whose sole job is to keep DNA organized. This coiled product is called a Nucleosome, which are then further coiled and packed together into long fibers call Chromatin. Chromatin then is further coiled into larger structures called Chromosomes. This organization is not only incredibly efficient, but it also provides functionality to the DNA itself. Chromosome and Chromatin architecture actually effects how DNA functions and communicates with the different systems in the cell, and the number of chromosomes is important to overall function of the DNA in an organism. Without this specific organization, Life could not exist. What does this mean? This means DNA could not have evolved and functioned without simultaneous organization. And DNA can't be organized without the proteins and systems that hold it all together. On top of that, the fact that how DNA is organized affects its function is a clear sign of foresight and planning - all clear signs of intelligent design. The more we learn about molecular biology, the more obvious it is that this was all Created intelligently.

Divinely Designed

78,665 views • 7 months ago

Chamath: Two terms you need to pay attention to in AI are Prefill and Decode “There's two terms that I think you're going to hear a ton about over these next few years.” “The first term is prefill, and the next is decode.” “What prefill and decode are, are two very distinct ways of how models think, and how a model goes through the process of answering a question that you ask it.” “And so when you send a prompt to AI, what happens is that the model processes it. This is called the reading phase or prefill.” “It reads your entire prompt all at once. And then it does a bunch of math, calculates all these relationships between all the words, and it stores them in temporary memory.” “The problem is that this is really compute bound. So it requires massive brute force. And Nvidia GPUs crush here.” “And their architecture is designed for massive parallel processing, which makes them really amazing at digesting these long prompts.” “So the problem just gets bigger and bigger, Nvidia just completely dominates.” “But the next phase though, this critical phase, the decode phase, is the writing phase, right?” “So the model starts to generate a response, you ask it a question and its response, one token at a time.” “And then to pick the next token to pick the next word, it has to look back at everything it has said already so that it doesn't hallucinate.” “The problem is that this is incredibly memory bandwidth constrained.” “And in our architecture, a long time ago, we made these design decisions from day one.” “And so what we did was we took a very different architectural approach, we took a very conservative process technology. We weren't pushing the boundaries of physics.” “And we used a lot of what's called SRAM. So memory on the chip so that we could do this decode thing as well or better than everybody else.” “And so now when you put these two things together, I just think it's going to create a huge acceleration in the ability for this entire infrastructure layer to get much cheaper and much more valuable, which I suspect then it'll have a lot more developer pull, you'll get a lot more applications being built, billions and billions of more people using it.”

The All-In Podcast

567,546 views • 7 months ago

From Scene One to Every Ending With You Trailer of New 5-Star Interactive Memory Series [Once Upon a Frame] Released! 🎞️Follow Love and Deepspace and Repost for a chance to win $50 (5 winners)! 🎞️Event Duration: From 05:00 on Jun. 17 to 04:59 on Jul. 2 (Server Time) You can select three out of the five event-limited 5-Star Memories: [Xavier: Runaway Hearts], [Zayne: Dawn and Devotion], [Rafayel: Sunset on Canvas], [Sylus: Finale Undone], and [Caleb: Up Close]. The drop rate of the 3 Memories you selected will be significantly increased. Each time you obtain a 5-Star Memory, there's a 75% chance it will be one of the three Memories you selected. *Notes: 1. During the event, you can change your selected Memories at any time. If you obtain a 5-Star Memory in a wish, there's a 25% chance that it will be an unselected Memory or a permanent 5-Star Memory. 2. After the event ends, the five event-limited Memories will not be obtainable through other means and will not enter the permanent Wish Pool: Xspace Echo. 3. The Wish event features Precise Wish and a pity system. For more details, please check the in-game rule page. 🎞️Cumulative Wish Rewards During the event, after making a certain number of Wishes, you can claim various rewards: Universal Hat [Unspoken Lines], Deepspace Wish: Limited*20, His [Memory-Themed Outfits], selectable [Event-Limited 5-Star Memory], and more. *The cumulative rewards are only available during this wish event. 🎞️Limited-Time Memory Growth Bonus During the event, by completing the growth tasks of the event-limited 5-Star Memories, you can claim various Upgrade and Ascension Materials. When the event-limited Memories reach Rank 1, you can claim the [Special-Colored Memory-Themed Outfit] for the corresponding love interest. *More content will be released with the version update. Please stay tuned! ——— 🪐Official Discord: 🪐Download and Log in Now: #LoveandDeepspace #OnceUponaFrame

Love and Deepspace

5,768,310 views • 2 months ago

Love and Deepspace | New Interactive 5-Star Memory🏖 [Zayne: Runaway Waves] No research project, no long distances—this is a summer where he is yours completely, just to waste time together. With one arm around you and the other steady at your waist, he carries you through the waves, leaving that exhilarating moment atop the highest point of the sea. "Your hand is the minimum requirement for safety, huh." 🏖You And Midsummer From 05:00 on Aug. 12 to 04:59 on Aug. 31 (Server Time) You can select three out of the five event-limited 5-Star Memories: [Xavier: Coolsplash Soak], [Zayne: Runaway Waves], [Rafayel: Heatwave Torrent], [Sylus: Lovespeed Ride], and [Caleb: Clearwind Glide]. The drop rate of the 3 Memories you selected will be significantly increased. Each time you obtain a 5-Star Memory, there's a 75% chance it will be one of the three Memories you selected. *Tips: 1. During the event, you can change your selected Memories at any time. If you obtain a 5-Star Memory in a wish, there's a 25% chance that it will be an unselected Memory or a permanent 5-Star Memory. 2. After the event ends, the five event-limited Memories will not be obtainable through other means and will not enter the permanent Wish Pool: Xspace Echo. 3. The Wish event features Precise Wish and a pity system. For more details, please check the in-game rule page. 🏖Cumulative Wish Rewards During the event, after making a certain number of Wishes, you can claim various rewards: Universal Hat [Summer Glow], [Deepspace Wish: Limited*20], His [Memory-Themed Outfits], selectable [Event-Limited 5-Star Memory], and more. *The cumulative rewards are only available during this wish event. 🏖Limited-Time Memory Growth Bonus During the event, by completing growth tasks of the event-limited 5-Star Memories, you can claim various Upgrade and Ascension Materials. When the event-limited Memories reach Rank 1, you can claim the [Special-Colored Memory-Themed Outfit] for the corresponding love interest! ☀️Linkon Summer Safety Reminder: The following scenes include dangerous actions. Please do not imitate unless accompanied by an Evolver. #LoveandDeepspace #YouAndMidsummer #Zayne

Love and Deepspace

556,611 views • 1 year ago