Skip to content
Steven AI Talk cover art

All episodes

Steven AI Talk, 712 episodes. Page 7 of 8.

#
Title
601

AI-Powered Entomology_ Reviewing Code with Large Language Models

602

Hiring AI Engineers in a Cheating World

603

Practical GraphRAG_ Smarter LLMs with Knowledge Graphs

604

Building Trust in AI Systems_ The XTOPS Framework

605

AI for Recommendation Systems and Search

606

Books Reimagined_ AI for New Reading Experiences

607

The OpenAI ChatGPT Agent_ A New Era of AI

608

Taxonomy for Next-Generation Reasoning Models

609

Instacart's LLM-Powered Search and Discovery Transformation

610

AI Agent Investment_ Walls and Logic

611

AI Agents for Real-Time Lead Generation

612

Innovating Recommendations_ LLMs, Semantic IDs, and Unified Models

613

Malware's Evolution_ Past, Present, and AI-Driven Future

614

Netflix's Unified Recommendation Model_ A Scalable Bet

615

Teaching Gemini to Recommend YouTube Videos

616

Agentic AI_ The Future of Human-AI Collaboration

617

Building a Ten-Person Unicorn Team

618

Winning the AI Product Knife Fight

619

AI Agent Use Cases_ IoT, RAG, and Disaster Response

620

Content-Aware Storage_ Unlocking AI's Potential with RAG

621

Spatial Intelligence_ The Next AI Frontier

622

The AI Model Life Cycle Explained

623

LLM Proxy Defenses_ Securing AI Usage

624

DeepSeek AI Banned Over GDPR Violations

625

Strategies for Enhancing AI Accuracy and Reliability

626

The Ideology and Business of AI

627

Marc Benioff's Race to One Billion AI Agents

628

Architecting Agent Memory_ Principles, Patterns, and Best Practices

629

OpenRouter_ Founding Story to Marketplace Innovation

630

Inside Meta_ A CFO's Vision for Growth and Innovation

631

AI vs_ Human Cognition_ A Comparative Analysis

632

Sam Altman_ Building AGI and the Future of OpenAI

633

ai in military applications

634

YC KARPATHY Software's Evolution_ From Code to AI Operating Systems.wav

635

The Evolution of Scale AI_ From Data to Agents

636

LANGCHAIN Building Reliable LLM Data Processing Pipelines

637

IBM Data Automation_ Best Practices for Efficiency and Scalability

638

Top AI Papers of the Week June 9-15, 2025

639

IBM AI Search_ From Keywords to RAG and Beyond

640

AI Agents_ Unstructured Data Transformation

641

LinkedIn's AI Agents_ Scaling Generative AI for Hiring

642

BlackRock's AI Agents for Asset Management with LangGraph

643

Modern Treasury AI_ Revolutionizing Financial Operations with LangGraph

644

Apple, Meta, and Quantum Computing Futures

645

Generative AI: Outlook, Opportunities, and Challenges

646

Reinforcement Pre-Training for Language Models

647

Sam Altman: The Stargate of AI Development

648

AI Fluency_ Frameworks and Foundations​​

649

IBM - AI Search Agents_ Tool Calling and MCP ​

650

Harari on AI, Humanity, and the Digital Exodus

651

Prompting, Vibe Coding, and AI Agents

652

Cursor: Building the Future of AI Coding with Claude

653

The Illusion of Thinking in Reasoning Models

654

Sequoia - OpenAI Codex Team: From Coding Autocomplete to Asynchronous Auto Agents

655

The Golden Age for Builders, Worse for Coders

656

Small vs. Large AI Models: Trade-offs & Use Cases Explained

657

RAFT: Adapting Language Model to Domain Specific RAG

658

Code Review and Refactoring with GitHub Copilot

659

IBM-What is Retrieval-Augmented Fine-Tuning (RAFT)?

660

⁠Barclays to roll out Microsoft 365 Copilot to 100,000 colleagues⁠

661

FAIR, DEEPMIND, CORNELL, NVIDIA How much do language models memorize?

662

How Anthropic teams use Claude Code

663

Top AI Papers of the Week

664

OpenThoughts_ Crafting Superior Reasoning Models

665

Snowflake Summit 2025_ Data, AI, and the Future

666

AI Developments_ Models, Tools, and Disputes

667

Understanding Open Source AI_ Transparency, Freedom, and Impact

668

Sundar Pichai: AI, Humanity, and Progress

669

Post-Training Methods for Large Language Models

670

Vec2Vec: Unsupervised Embedding Translation

671

Thinkless: LLM Learns When to Think

672

Building the AI Bank of the Future

673

AI in Financial Services: Risks and Opportunities

674

AI Innovation in Financial Services

675

Prompting, Vibe Coding, and AI Agents

676

The Leaderboard Illusion

677

Fin-R1 Financial Reasoning with a Lightweight Language Model

678

Mechanistic Interpretability via Cross-Layer Feature Attribution Graphs

679

Tracing the Thoughts of a Large Language Model

680

Magma is the first-ever foundation model for multimodal AI agents

681

Experimental Economics_ Core Concepts and Applications

682

The Psychology and Economics of Incentives

683

Market Experiments, Asymmetric Information, and Auction Theory

684

Behavioral Economics_ Trust, Motivation, Willpower, and Gender

685

Experimental Economics_ Game Theory, Trust, and Decision Making

686

Game Theory_ Strategic Decisions, Equilibria, and Experimental Data

687

Beyond Homo Economicus_ Social Preferences and Game Theory

688

Risk, Time Preferences, and Experimental Methodology

689

Experimental Economics_ Design, Validity, and Types

690

Behavioral Economics_ Heuristics, Prospect Theory, and the Endowment Effect

691

Experimental and Behavioral Economics_ An Introduction

692

NASA-Examining Proposed Uses of LLMs to Produce or Assess Assurance Arguments

693

hallucination and rag - debate version podcast

694

hallucination and rag - executive version podcast

695

hallucination and rag - summary version podcast

696

International AI Safety Report

697

Transfusion A Multi Modal Generative Model

698

What is EU COMPASS about?

699

How Safe is AI? Deep Dive into AirBench 2024 🚦🤖

700

A Survey of KAN - Unlocking the Power of Kolmogorov-Arnold Networks (CANs)