Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Memory isn’t just a feature in AI, it’s the difference between a system that responds and one that truly understands. In the first episode of The Long Walk, Sudarshan Kamath and I dive into how memory is shaping the next generation of voice agents, and why it’s becoming critical... show more

Nishkarsh

8,886 subscribers

30,288 views • 6 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

AI agents are quickly becoming a new layer of the enterprise workforce. In our partner podcast episode with Salesforce, we explored what it takes to make that shift real. 3 key insights: • Enterprise content gives AI the context it needs • The biggest gains come from content-heavy workflows • Governance must scale as agents take action Dive into how Box + Salesforce are thinking about the future of enterprise AI →

AI agents are quickly becoming a new layer of the enterprise workforce. In our partner podcast episode with Salesforce, we explored what it takes to make that shift real. 3 key insights: • Enterprise content gives AI the context it needs • The biggest gains come from content-heavy workflows • Governance must scale as agents take action Dive into how Box + Salesforce are thinking about the future of enterprise AI →

Box

883,519 views • 5 months ago

Meet the minds building supermemory! 🧠 Our research engineer Prasanna breaks down how memory actually works, in your head, and in AI. inside the episode: → why forgetting is a feature and not a failure → what your hippocampus inside brain is really doing all day → how "dreaming" turns a messy day into long-term memory → what the AI labs get right, and wrong, when they copy the brain → why a bigger context window still isn't memory the line worth sitting with: stop asking where memory is stored. start asking what gets kept, and why the brain chose it. full episode below ↓

Meet the minds building supermemory! 🧠 Our research engineer Prasanna breaks down how memory actually works, in your head, and in AI. inside the episode: → why forgetting is a feature and not a failure → what your hippocampus inside brain is really doing all day → how "dreaming" turns a messy day into long-term memory → what the AI labs get right, and wrong, when they copy the brain → why a bigger context window still isn't memory the line worth sitting with: stop asking where memory is stored. start asking what gets kept, and why the brain chose it. full episode below ↓

supermemory

13,926 views • 1 month ago

Aaron Levie is one of the greats. He’s been the co-founder and CEO of Box for 20 years, of which public CEO for 10. And he shows no signs of slowing down, as one of the most active CEOs thinking about how AI agents will shape enterprise software. In our Greylock Partners Change Agents, Aaron and I discussed the question: happens when SaaS is no longer built for humans, but for a much larger scale of agents and humans orchestrating those agents? A few of my favorite topics from the episode: - Why 90%+ of enterprise data has gone unused to date and how agents finally make it accessible - Why SaaS categories won’t disappear, but will be rebuilt around agent orchestration layers - Why the system of record doesn't lose importance, but gains importance the enable agents - How abundance (not labor replacement) is the real shift agents bring to knowledge work - And the real moat in the agent era may be neither the model nor the interface but the workflow memory the agent accumulates over time Aaron has one of the clearest, most grounded takes on where agents for the enterprise can go and what happens to traditional enterprise SaaS. Full episode below:

Aaron Levie is one of the greats. He’s been the co-founder and CEO of Box for 20 years, of which public CEO for 10. And he shows no signs of slowing down, as one of the most active CEOs thinking about how AI agents will shape enterprise software. In our Greylock Partners Change Agents, Aaron and I discussed the question: happens when SaaS is no longer built for humans, but for a much larger scale of agents and humans orchestrating those agents? A few of my favorite topics from the episode: - Why 90%+ of enterprise data has gone unused to date and how agents finally make it accessible - Why SaaS categories won’t disappear, but will be rebuilt around agent orchestration layers - Why the system of record doesn't lose importance, but gains importance the enable agents - How abundance (not labor replacement) is the real shift agents bring to knowledge work - And the real moat in the agent era may be neither the model nor the interface but the workflow memory the agent accumulates over time Aaron has one of the clearest, most grounded takes on where agents for the enterprise can go and what happens to traditional enterprise SaaS. Full episode below:

Corinne Marie Riley

43,790 views • 8 months ago

.Secretary Kennedy: “There’s a big difference between established science and the scientific establishment. We all know that trusting the experts is not a feature of science; it’s not a feature of democracy — it’s a feature of tyranny.”

.Secretary Kennedy: “There’s a big difference between established science and the scientific establishment. We all know that trusting the experts is not a feature of science; it’s not a feature of democracy — it’s a feature of tyranny.”

HHS Rapid Response

152,624 views • 7 months ago

Episode 1 of memory 101: the anatomy of memory.🧠 real memory isn't one thing. it's five: > facts > profiles > relationships > temporality > forgetting "AI memory" products build one of these primitives and stop. Real memory is when all five compose. Next, stay tuned for RAG ↓

Episode 1 of memory 101: the anatomy of memory.🧠 real memory isn't one thing. it's five: > facts > profiles > relationships > temporality > forgetting "AI memory" products build one of these primitives and stop. Real memory is when all five compose. Next, stay tuned for RAG ↓

supermemory

21,646 views • 2 months ago

Introducing Memory 101 🧠 Every ai tool you use is a goldfish. brilliant for one chat, close the tab and it forgets you completely. memory is the most underbuilt layer in ai right now. so we're explaining how it actually works, one episode at a time. coming up: → rag vs memory, why most "ai memory" is just search → the 5 things real memory needs: facts, profiles, graphs, time, forgetting → why good memory has to forget things follow along!

Introducing Memory 101 🧠 Every ai tool you use is a goldfish. brilliant for one chat, close the tab and it forgets you completely. memory is the most underbuilt layer in ai right now. so we're explaining how it actually works, one episode at a time. coming up: → rag vs memory, why most "ai memory" is just search → the 5 things real memory needs: facts, profiles, graphs, time, forgetting → why good memory has to forget things follow along!

supermemory

17,235 views • 2 months ago

How important is data accuracy in crypto? In this episode, Wanja S. Oberhof of sqd.ai explains why correct blockchain data is becoming critical for trading, AI, and the next generation of onchain applications. #CHAINREACTION Watch now 👇

How important is data accuracy in crypto? In this episode, Wanja S. Oberhof of sqd.ai explains why correct blockchain data is becoming critical for trading, AI, and the next generation of onchain applications. #CHAINREACTION Watch now 👇

Cointelegraph

73,796 views • 1 month ago

Everyone wants AI with a bigger memory, we think that's the wrong goal.. We sat down with Soham Daga, AI researcher at supermemory, for a deep dive into how machines actually remember you. what we get into: - why every AI forgets you - why forgetting is the hard part, not remembering - memory that understands time - going past reranking with aggregation - buckets for agent memory - SMFS, cutting tokens by 60% A conversation on the future of context, full episode below!

Everyone wants AI with a bigger memory, we think that's the wrong goal.. We sat down with Soham Daga, AI researcher at supermemory, for a deep dive into how machines actually remember you. what we get into: - why every AI forgets you - why forgetting is the hard part, not remembering - memory that understands time - going past reranking with aggregation - buckets for agent memory - SMFS, cutting tokens by 60% A conversation on the future of context, full episode below!

supermemory

20,600 views • 22 days ago

Yesterday, I joined TBPN to talk about what it really means to give AI a memory. And, why that’s becoming the next big moat. We discussed: - Why today’s AI apps are stateless - How memory is quickly becoming the real moat for AI systems - How Mem0 is decoupling memory from models - Why users should be able to own and carry their AI memories across apps - And, how 200 cold emails changed my life🙂 Appreciate John Coogan, Jordi Hays & the TBPN team for having me and for such a thoughtful discussion around the future of AI infrastructure.

Yesterday, I joined TBPN to talk about what it really means to give AI a memory. And, why that’s becoming the next big moat. We discussed: - Why today’s AI apps are stateless - How memory is quickly becoming the real moat for AI systems - How Mem0 is decoupling memory from models - Why users should be able to own and carry their AI memories across apps - And, how 200 cold emails changed my life🙂 Appreciate John Coogan, Jordi Hays & the TBPN team for having me and for such a thoughtful discussion around the future of AI infrastructure.

Taranjeet

14,913 views • 10 months ago

Unpopular opinion: The current school system is designed for the average, not the exceptional. Joséf survived the system, but he could have thrived if they offered a better way. 🇳🇬 Traditional tutoring is 2 standard deviations better than classroom learning, but it’s too expensive for 99% of families. OLi is changing that. Real-time voice, screen-reading, and long-term memory. It’s the "2-Sigma" boost for the price of a coffee. ☕️📈 Watch Joseph explain why the next generation of Nigerian leaders will be AI-powered. OLi Nigeria 🇳🇬 🇳🇬 Check the link in bio to join the pre registration list! 🚀 #Nigeria #AITutor #EducationReform #2SigmaAdvantage #TechUpdate2026

Unpopular opinion: The current school system is designed for the average, not the exceptional. Joséf survived the system, but he could have thrived if they offered a better way. 🇳🇬 Traditional tutoring is 2 standard deviations better than classroom learning, but it’s too expensive for 99% of families. OLi is changing that. Real-time voice, screen-reading, and long-term memory. It’s the "2-Sigma" boost for the price of a coffee. ☕️📈 Watch Joseph explain why the next generation of Nigerian leaders will be AI-powered. OLi Nigeria 🇳🇬 🇳🇬 Check the link in bio to join the pre registration list! 🚀 #Nigeria #AITutor #EducationReform #2SigmaAdvantage #TechUpdate2026

OLi by Olympus Insights

10,695 views • 7 months ago

“Saudi Made” isn’t just a label. It’s a bold declaration that the future is being built right in this land. We’re working with top-tier partners, building world-class components, and powering the next generation of devices from the Kingdom. See how we’re shaping tomorrow:

“Saudi Made” isn’t just a label. It’s a bold declaration that the future is being built right in this land. We’re working with top-tier partners, building world-class components, and powering the next generation of devices from the Kingdom. See how we’re shaping tomorrow:

Alat | #TomorrowMadeBetter

6,393,565 views • 1 year ago

When technique becomes poetry 🎸✨ Tremolo isn’t just speed — it’s the illusion of a never-ending voice. A single note, repeated with such control and delicacy that it begins to sing, floating above a steady pulse like a memory that refuses to fade. In mastering tremolo, the goal isn’t just precision — it’s beauty. The seamless flow, the breath between phrases, the way each note melts into the next… until you no longer hear the technique, only the music. This is where the guitar stops being percussive — and starts to feel like a human voice. #ClassicalGuitar #Tremolo #Fingerstyle #Guitar #MusicArt #Lyrical

When technique becomes poetry 🎸✨ Tremolo isn’t just speed — it’s the illusion of a never-ending voice. A single note, repeated with such control and delicacy that it begins to sing, floating above a steady pulse like a memory that refuses to fade. In mastering tremolo, the goal isn’t just precision — it’s beauty. The seamless flow, the breath between phrases, the way each note melts into the next… until you no longer hear the technique, only the music. This is where the guitar stops being percussive — and starts to feel like a human voice. #ClassicalGuitar #Tremolo #Fingerstyle #Guitar #MusicArt #Lyrical

🎶𝗖𝗹𝗮𝘀𝘀𝗶𝗰𝗮𝗹 𝗠𝗲𝗹𝗼𝗱𝗶𝗲𝘀 ✨

11,149 views • 4 months ago

How do AI agents actually take action? First, they have to see. Cognitive scientist Dr. Danielle Perszyk and AI researcher Matthew Elkherj dive into one of the most underestimated challenges in building AI agents: perception. Episode 3 of Making a Mind explores how agents learn to interpret the web—and why it matters. 🎧

How do AI agents actually take action? First, they have to see. Cognitive scientist Dr. Danielle Perszyk and AI researcher Matthew Elkherj dive into one of the most underestimated challenges in building AI agents: perception. Episode 3 of Making a Mind explores how agents learn to interpret the web—and why it matters. 🎧

Amazon News

25,217 views • 7 months ago

- Before I unveil the date of the drop, let me take you down memory lane — through the grind, the setbacks, and the moments that changed everything. This isn’t just another launch. It’s a streetwear collaboration rooted in story and legacy — a journey that shaped me and led to the rise of the Sultan of Swing. Immensely proud of the Movement team for crafting a streetwear line that truly reflects who I am and what I stand for... #92collection #wasimakram #movement Movement

- Before I unveil the date of the drop, let me take you down memory lane — through the grind, the setbacks, and the moments that changed everything. This isn’t just another launch. It’s a streetwear collaboration rooted in story and legacy — a journey that shaped me and led to the rise of the Sultan of Swing. Immensely proud of the Movement team for crafting a streetwear line that truly reflects who I am and what I stand for... #92collection #wasimakram #movement Movement

Wasim Akram

34,067 views • 7 months ago

The design tells the story. If comparing prices is harder than it should be, consumers make different choices. And sometimes that friction isn’t a bug in the system. It’s a feature of the system.⁣ ⁣

The design tells the story. If comparing prices is harder than it should be, consumers make different choices. And sometimes that friction isn’t a bug in the system. It’s a feature of the system.⁣ ⁣

Justin Wolfers

15,456 views • 2 months ago

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:

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

131,965 views • 1 year ago

$5.9M for a Brisbane Shitbox? The housing market isn’t just broken—it’s a rigged casino. The self-imposed destruction of our social contract is happening in real time, and the next generation is paying the price.

$5.9M for a Brisbane Shitbox? The housing market isn’t just broken—it’s a rigged casino. The self-imposed destruction of our social contract is happening in real time, and the next generation is paying the price.

Scotty Chal

22,152 views • 1 year ago

The next generation of the suite is here...NetSuite Next! It’s where your business meets AI. Ask Oracle, SuiteAgents, AI Canvas, and more turn your system of record into a system of insight, action, and collaboration. Get ready for what’s 𝘯𝘦𝘹𝘵:

The next generation of the suite is here...NetSuite Next! It’s where your business meets AI. Ask Oracle, SuiteAgents, AI Canvas, and more turn your system of record into a system of insight, action, and collaboration. Get ready for what’s 𝘯𝘦𝘹𝘵:

NetSuite

17,846 views • 11 months ago

The line between the first and the third world is blurring. In the “first world” I cannot walk around safely because of mass migration. How is that first world? Because I can drink water out of the sink? Give me a break. The first world is becoming a MESS and now the former “third world” is becoming the new “first world”.

The line between the first and the third world is blurring. In the “first world” I cannot walk around safely because of mass migration. How is that first world? Because I can drink water out of the sink? Give me a break. The first world is becoming a MESS and now the former “third world” is becoming the new “first world”.

Joey Mannarino

23,184 views • 4 months ago