Ever wonder what it's REALLY like inside the world of tech startups? Join Daniel Davis and Brennan Woodruff, the COO of GoCharlie (a generative AI startup), for a brutally honest conversation about the realities of creating an AI startup versus the usual Silicon Valley tech hype. Brennan shares his unique journey from KPMG to Uber, then to SoftBank's Vision Fund, and finally into the world of generative AI. They dive deep into the harsh realities of the tech industry, the surprising camaraderie between Uber and Lyft employees, and the overwhelming competition and noise within the AI space. This is a must-watch for anyone interested in tech, startups, AI, or just a behind-the-scenes look at Silicon Valley thinking and what it takes to build a company in today's world. 🔗 Brennan's Links: ➡️ LinkedIn: https://www.linkedin.com/in/brennan-m-woodruff? ➡️ X: https://x.com/BrennanWoodruff 🔗 GoCharlie Links: ➡️ Website: https://gocharlie.ai/ 🔗 TrustGraph Links: ➡️ GitHub: https://github.com/trustgraph-ai/trustgraph ➡️ TrustGraph Config UI: https://config-ui.demo.trustgraph.ai/ ➡️ Website: https://trustgraph.ai/ ➡️ Discord: https://discord.gg/sQMwkRz5GX ➡️ Bluesky: https://bsky.app/profile/trustgraph.bsky.social ➡️ Blog: https://blog.trustgraph.ai ➡️ LinkedIn: https://www.linkedin.com/company/trustgraph/
knowledge graphs with linear algebra and how it will impact RAG and explainability with LLMs. Is matrix multiplication the most effective way to query knowledge? Is Cypher or GQL the future of query languages?
Topics:
00:00 Intros
07:03 A different way of storing knowledge with FalkorDB
11:15 GraphBLAS
13:10 Sparse Matrices and Zeroes
17:35 Connecting linear algebra to Cypher
21:32 Semantic search and HNSW
26:04 Latency and knowledge graph queries
30:20 "The lack of explainability is disturbing"
34:18 Hybrid RAG systems
37:46 The focus will be on GraphRAG 🔗 FalkorDB Links: ➡️ Website: https://www.falkordb.com/ ➡️ GitHub: https://github.com/FalkorDB/FalkorDB ➡️ X/Twitter: https://x.com/falkordb ➡️ LinkedIn: https://www.linkedin.com/company/falkordb/ ➡️ Edges, GraphBLAS, spare matrices: https://www.falkordb.com/blog/edges-in-falkordb/ 🔗 TrustGraph Links: ➡️ GitHub: https://github.com/trustgraph-ai/trustgraph ➡️ TrustGraph Config UI: https://config-ui.demo.trustgraph.ai/ ➡️ Website: https://trustgraph.ai/ ➡️ Discord: https://discord.gg/sQMwkRz5GX
➡️ Bluesky: https://bsky.app/profile/trustgraph.bsky.social ➡️ Blog: https://blog.trustgraph.ai ➡️ LinkedIn: https://www.linkedin.com/company/trustgraph/
The Co-founder and CTO of Memgraph, Marko Budiselić, joins us to talk all things knowledge graphs, evaluation metrics for AI, and whether or not AI can be considered AGI if it's not a cyber-physical system. Topics: 0:00:00 Intros 0:04:10 "Knowledge" vs. "Data" 0:07:15 Lateral thinking and interpretation 0:10:48 Datastores, Databases, Data Lakes, and Data Warehouses 0:13:55 "Knowledge graph" is an abstract term 0:17:10 Building a knowledge graph database from scratch 0:19:43 The quest for speed 0:23:15 Zero to MVP 0:26:50 There was always noise 0:29:20 Is legal actually a good use case for AI? 0:32:33 LLMs make everyone a developer 0:37:13 Things never work out the way you think they will 0:42:06 So many metrics 0:47:03 Cracking open the "black box" 0:50:04 Lawyers and engineers agree! 0:53:42 LLM efficiency gains are a given 0:56:56 AGI has been 3 months away for decades 🔗 Memgraph Links: ➡️ Website: https://memgraph.com
➡️ GitHub: https://github.com/memgraph/memgraph
➡️ Discord: https://discord.gg/memgraph
➡️ LinkedIn: https://www.linkedin.com/company/memgraph 🔗 TrustGraph Links: ➡️ GitHub: https://github.com/trustgraph-ai/trustgraph ➡️ TrustGraph Config UI: https://config-ui.demo.trustgraph.ai/ ➡️ Website: https://trustgraph.ai/ ➡️ Discord: https://discord.gg/sQMwkRz5GX ➡️ Blog: https://blog.trustgraph.ai ➡️ LinkedIn: https://www.linkedin.com/company/trustgraph/
Taking a break from data engineering and RAG, Daniel spoke with Rick Borden, an attorney from Frankfurt Kurnit Klein & Selz, on the state of AI regulations in 2024. Is it really the wild west in enterprise contracts around AI now? How do AI innovators navigate through these chaotic times? Which sci-fi book most accurately described the current state of AI? And will quantum computers make everything we just said irrelevant?
🔗 Rick's Links: ➡️ Rick Borden — Frankfurt Kurnit Klein & Selz: https://fkks.com/attorneys/richard-borden ➡️ Face Value: AI and Facial Recognition Technology Claims Draw FTC Scrutiny by Andrew Folks: https://technologylaw.fkks.com/post/102jqln/face-value-ai-and-facial-recognition-technology-claims-draw-ftc-scrutiny ➡️ FTC Announces AI Sweep by Hannah Taylor: https://technologylaw.fkks.com/post/102jknz/ftc-announces-ai-sweep ➡️ SEC Receives Major Blow in SolarWinds Case by Rick Borden: https://technologylaw.fkks.com/post/102je3h/sec-receives-major-blow-in-solarwinds-case 🔗 TrustGraph Links: ➡️ GitHub: https://github.com/trustgraph-ai/trustgraph ➡️ TrustGraph Config UI: https://config-ui.demo.trustgraph.ai/ ➡️ Documentation: https://trustgraph.ai/ ➡️ Discord: https://discord.gg/sQMwkRz5GX ➡️ Blog: https://blog.trustgraph.ai ➡️ LinkedIn: https://www.linkedin.com/company/trustgraph/
The founders of TrustGraph, Daniel Davis and Mark Adams, discuss their journeys with big data, knowledge graphs, and data engineering. Knowledge graphs are hard to learn - no matter what Mark says, and he gives everyone a crash course on them, why querying graphs is tricky, and what makes for reliable data services. The conversation ends with a discussion of what makes for "explainable AI" and the future of AI security. Topics: 0:00:00 Introductions 0:03:25 Mark's background 0:06:23 Are Knowledge Graph's more popular in Europe? 0:08:27 Past data engineering lessons learned 0:17:15 Knowledge Graphs aren't new 0:22:42 Knowledge Graph types and do they matter? 0:27:10 The case for and against Knowledge Graph ontologies 0:39:40 The basics of Knowledge Graph queries 0:45:42 Knowledge about Knowledge Graphs is tribal 0:47:50 Why are Knowledge Graphs all of a sudden relevant with AI? 0:53:45 Some LLMs understand Knowledge Graphs better than others 0:58:30 What is scalable and reliable infrastructure? 1:01:45 What does "production grade" mean? 1:04:45 What is Pub/Sub? 1:09:40 Agentic architectures 1:12:17 Autonomous system operation and reliability 1:16:50 Simplifying complexity 1:19:48 A new paradigm for system control flow 1:23:45 Agentic systems are "black boxes" to the user 1:24:55 Explainability in agentic systems 1:30:05 The human relationship with agentic systems 1:32:00 What does cybersecurity look like for an agentic system? 1:35:30 Prompt injection is the new SQL injection 1:37:00 Explainability and cybersecurity detection 1:39:40 Systems engineering for agentic architectures is just beginning 🔗 TrustGraph Links: ➡️ GitHub: https://github.com/trustgraph-ai/trustgraph ➡️ TrustGraph Config UI: https://config-ui.demo.trustgraph.ai/ ➡️ Website: https://trustgraph.ai/ ➡️ Discord: https://discord.gg/sQMwkRz5GX ➡️ Blog: https://blog.trustgraph.ai ➡️ LinkedIn: https://www.linkedin.com/company/trustgraph/
Daniel Davis of TrustGraph and Kirk Marple from Graphlit discuss the 2024 state of RAG. Whether it's RAG, GraphRAG, or HybridRAG, a lot has changed since the term has become ubiquitous in AI. Where are we, where are we going, and where should be going are all answered in this discussion. 00:00 00:20 Introductions 04:10 The Term "RAG" Itself 06:20 Long Context Windows 08:10 Claude 3.5 Haiku 11:20 LLM Pricing Variance 14:11 What Happened to Claude 3 Opus? 19:03 AI Maturity 23:22 What is AGI? 26:40 Entity Extraction with LLMs 32:18 RDF? Cypher? Something else? 36:36 Why so many new GraphDBs and VectorDBs? 42:23 Reinventing the Wheel 42:48 "You Don't Need LangChain" 44:20 How to Promote Emerging Projects 46:53 "Hype Matters" 49:15 Where is RAG 1 Year from Now 54:09 Should AI Model Itself on Human Cognition? 58:45 The DARPA MUC AI Conferences 🔗 Graphlit Links: ➡️ Website: https://graphlit.com 🔗 Kirk's Links: ➡️ Twitter: https://x.com/kirkmarple 🔗 Daniel's Links: ➡️ Twitter: https://x.com/trustspooky 🔗 TrustGraph Links: ➡️ GitHub: https://github.com/trustgraph-ai/trustgraph ➡️ TrustGraph Config UI: https://config-ui.demo.trustgraph.ai/ ➡️ Website: https://trustgraph.ai/ ➡️ Discord: https://discord.gg/sQMwkRz5GX ➡️ Blog: https://blog.trustgraph.ai ➡️ LinkedIn: https://www.linkedin.com/company/trustgraph/