Ben Greenberg
How to Decipher User Uncertainty with GenAI and Vector Search
#1about 4 minutes
Why traditional search fails with ambiguous data and queries
Both vague user search queries and poorly structured source data create ambiguity that traditional keyword-based systems cannot effectively resolve.
#2about 5 minutes
Understanding vector embeddings and measuring semantic closeness
Vector embeddings represent data as numerical lists, enabling the measurement of conceptual closeness using mathematical formulas like Euclidean and cosine distance.
#3about 4 minutes
How embedding models capture context and relationships
Embedding models like GPT use transformer layers and neural network principles to analyze input and generate vector embeddings that capture semantic meaning.
#4about 5 minutes
Vector search as the memory layer for RAG and Agentic AI
Vector search provides the essential memory component for both Retrieval-Augmented Generation (RAG) and Agentic AI, which also require tools and planning capabilities.
#5about 3 minutes
The risks of centralized control over AI models
Centralized, closed-source control over how embedding models are trained and weighted poses a significant risk to the future of information and understanding.
#6about 3 minutes
Exploring open source and decentralized AI alternatives
Decentralized and open-source platforms for AI compute and model training offer an alternative to closed systems, preserving user autonomy and control.
Related jobs
Jobs that call for the skills explored in this talk.
Wilken GmbH
Ulm, Germany
Senior
Kubernetes
AI Frameworks
+3
Picnic Technologies B.V.
Amsterdam, Netherlands
Intermediate
Senior
Python
Structured Query Language (SQL)
+1
Matching moments
03:15 MIN
The future of recruiting beyond talent acquisition
What 2025 Taught Us: A Year-End Special with Hung Lee
04:57 MIN
Increasing the value of talk recordings post-event
Cat Herding with Lions and Tigers - Christian Heilmann
14:06 MIN
Exploring the role and ethics of AI in gaming
Devs vs. Marketers, COBOL and Copilot, Make Live Coding Easy and more - The Best of LIVE 2025 - Part 3
04:06 MIN
Using AI to enable human connection in recruiting
Retention Over Attraction: A New Employer Branding Mindset
03:09 MIN
Questioning the purpose of Meta's AI-only feed
WeAreDevelopers LIVE – Frontend Inspirations, Web Standards and more
05:17 MIN
Shifting from traditional CVs to skill-based talent management
From Data Keeper to Culture Shaper: The Evolution of HR Across Growth Stages
08:18 MIN
The impact of AI on tech recruitment and resumes
Slopquatting, API Keys, Fun with Fonts, Recruiters vs AI and more - The Best of LIVE 2025 - Part 2
04:28 MIN
Building an open source community around AI models
AI in the Open and in Browsers - Tarek Ziadé
Featured Partners
Related Videos
Enter the Brave New World of GenAI with Vector Search
Mary Grygleski
GenAI Security: Navigating the Unseen Iceberg
Maish Saidel-Keesing
Should we build Generative AI into our existing software?
Simon Müller
GenAI Unpacked: Beyond Basic
Damir
Develop AI-powered Applications with OpenAI Embeddings and Azure Search
Rainer Stropek
Semantic AI: Why Embeddings Might Matter More Than LLMs
Christian Weyer
Build RAG from Scratch
Phil Nash
Make it simple, using generative AI to accelerate learning
Duan Lightfoot
Related Articles
View all articles



From learning to earning
Jobs that call for the skills explored in this talk.

INTENT HQ
Barcelona, Spain
TypeScript
Amazon Web Services (AWS)


The Rolewe
Charing Cross, United Kingdom
API
Python
Machine Learning




Amazon.com Inc.
XML
HTML
JSON
Python
Data analysis
+1

Amazon.com Inc.
XML
HTML
JSON
Python
Data analysis
+1
