The Trust Moat Podcast
Gartner predicts that 40% of agentic AI projects will be canceled by 2027—not because the models aren't smart enough, but because the underlying memory layer isn't ready. In this episode, we sit down with Nemanja Bibic, Head of Growth at Cognee, a startup building the knowledge layer for our agentic future, to discuss the urgent need for a "hippocampus" for artificial intelligence. We dive deep into why current LLMs suffer from "AI Alzheimer’s," the technical difference between stateless and stateful versions, and why better memory—not just bigger models—is the key to reaching AGI. Inside the Episode * The "AI Alzheimer’s" Effect: Why current models struggle to retain context beyond 48 hours and act as a blank slate every time you open them. * The $7.5M Infrastructure Bet: Why founders from OpenAI and Facebook AI Research are backing the development of a "cognitive infrastructure". * Neurological vs. Cognitive Mimicry: How mimicking human reasoning and learning processes is moving AI accuracy from 60% toward 100%. * The Economics of Memory: Why the next trillion-dollar companies will be the ones building the infrastructure that allows AI to learn, doubt itself, and function without constant human supervision. * Community-Driven Intelligence: How 12,000 developers are building a persistent memory layer for the future of agentic workflows. Prefer watching the conversation? Subscribe to our YouTube channel: https://www.youtube.com/@TheTrustMoatPod ⏱️ Chapters: 00:00:00 [https://www.youtube.com/watch?v=ET7Ijpb0gI4] Intro 00:03:40 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=220s] CHAPTER 1 - WHY YOUR AI HAS AMNESIA 00:05:15 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=315s] The "48-Hour Wipe": Why LLMs lose context over time 00:08:30 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=510s] Stateless vs. Stateful: The technical root of AI memory loss 00:14:22 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=862s] Why "Long Context Windows" aren't a permanent fix 00:25:42 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=1542s] CHAPTER 2 - THE $7.5M BET ON A PROBLEM NOBODY'S TALKING ABOUT 00:27:10 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=1630s] Why OpenAI and FAIR founders are backing memory infrastructure 00:29:45 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=1785s] Identifying the "infrastructure gap" in the current AI stack 00:32:15 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=1935s] The business risk of building on "forgetful" models 00:34:47 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=2087s] CHAPTER 3 - WHAT "AI MEMORY" ACTUALLY MEANS 00:36:12 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=2172s] Vector Databases vs. Knowledge Graphs: A breakdown 00:38:50 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=2330s] The role of "Ontologies" in making AI understand your business 00:40:05 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=2405s] Ephemeral vs. Persistent memory in agentic workflows 00:42:08 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=2528s] CHAPTER 4 - HOW THE HUMAN BRAIN INSPIRED A FIX FOR BROKEN AI MEMORY 00:44:10 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=2650s] Mimicking the Hippocampus: Building a digital long-term memory 00:46:55 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=2815s] How "Cognitive Mimicry" beats simple "Neurological Mimicry" 00:49:30 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=2970s] The "Self-Doubt" Mechanism: Teaching AI to know what it doesn't know 00:52:48 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=3168s] CHAPTER 5 - 12,000 DEVELOPERS WHO CHOSE TO BUILD THIS FOR FREE 00:54:20 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=3260s] The Open Source advantage in AI security and memory 00:58:15 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=3495s] Why community-driven "Maltbots" are outpacing corporate labs 01:03:40 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=3820s] Collaborative Intelligence: Lessons from 12k contributors 01:07:54 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=4074s] CHAPTER 6 - THE RACE BENEATH THE RACE: MEMORY VS MODELS 01:09:15 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=4155s] Commodity Models: Why intelligence is becoming a "race to zero" 01:11:05 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=4265s] Proprietary Data + Memory: The only defensible moat left 01:13:39 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=4419s] CHAPTER 7 - WHAT YOUR COMPANY SHOULD DO BEFORE LOCKING IN AN AI STACK 01:15:20 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=4520s] The Gartner Warning: Avoiding the 40% project failure rate 01:18:45 [https://www.youtube.com/watch?v=ET7Ijpb0gI4&t=4725s] Evaluating your "Memory Layer" before you buy the model 01:21:10 Future-proofing your agentic infrastructure Follow Nemanja Bibic on : * LinkedIn: https://www.linkedin.com/in/nemanja-bibic-20523b87/ [https://www.linkedin.com/in/nemanja-bibic-20523b87/] * Check out Cognee: https://www.cognee.ai/ [https://www.youtube.com/redirect?event=video_description&redir_token=QUFFLUhqa2Z0ZE5oWlR4X0oxaFp4b29uVXZqQU5kb0RRQXxBQ3Jtc0tuNVNqcDUxVTU2d21KaE12NDlaWnBmN214RFpnQVhJaXZwVVhjQTJwSkZZd1dLeDFUc0ZSZ3JWMUl1dnhycFQ1NHVoU0ZIczl3OHlBQUZzYUlUaTNfQXFPRVltbGRoc3puc3FWS1NkS1Bpb2FVTE9XZw&q=https%3A%2F%2Fwww.cognee.ai%2F&v=ET7Ijpb0gI4] Connect with Maja on: * LinkedIn: https://www.linkedin.com/in/zmajapbaines/ * X: https://x.com/lazarevic_p?s=11 [https://www.youtube.com/redirect?event=video_description&redir_token=QUFFLUhqa203NENXbFFwdnc4SFRZU1FiNEhMekNqbEh3UXxBQ3Jtc0ttYm9hY1pJanVYSkdTN2t6N3R0NUhtZlhkcHBmZ0V6emdEMTBQMEw0SEs1eVRGdkJuaVdza0QzWk5ucENJYnJoMkRlUkZEXzU2b2pFMWx2bjZvaDFjaG1KN2VmMHI4X1U5VFlTcHZQZVhaMllfU0xaRQ&q=https%3A%2F%2Fx.com%2Flazarevic_p%3Fs%3D11&v=ET7Ijpb0gI4] * Instagram: https://www.instagram.com/majaperovicbaines_mbm [https://www.instagram.com/majaperovicbaines_mbm]
6 episodios
Comentarios
0Sé la primera persona en comentar
¡Regístrate ahora y únete a la comunidad de The Trust Moat Podcast!