All Episodes
Build Wiz AI Show — 229 episodes
Pacing the Frontier: A Blueprint for Measured AI Progress
The AI Agent Harness
@skills: An Open Protocol for Agent Skill Delivery
Policy on the AI Exponential
The Rise of Recursive Self-Improvement at Anthropic
AlphaProof Nexus: Advancing Mathematics Research via AI Formal Proof Search
Pi - and self-modifying AI Agents
Code with Claude - London 2026
Google I/O 2026 keynote
The Langchain Agent Development Keynote 2026
Building the Software Factory: From Code to Autonomy
Spec-Driven Development and Agentic Workflows in 2026
Efficient Pre-Training with Token Superposition
Skills at Scale: Building and Scaling Agentic Workflows
Jensen Huang on the AI Revolution 2026
Robotics' End Game: The Great Parallel to AGI
Andrej Karpathy at Sequoia - AI Ascent 2026: From Vibe Coding to Agentic Engineering
The Cognitive Revolution: Sequoia AI Ascent 2026 Keynote
Demis Hassabis on the Roadmap to General Intelligence
AHE: Observability-Driven Evolution of Coding-Agent Harnesses
Claude Mythos Preview
Anthropic Econimic Index Report 03/2026
How to Ship Complex Features 10x Faster with AI Agents
The Era of AI Psychosis and Agentic Leverage
Attention Residuals - from Kimi
Why long context make AI dumber
How Coding Agents Are Reshaping Engineering, Product and Design
Securing AI Agents and Execution Engine
The Blueprint for Engineering reliable AI Agents
The complete guide to build skills for AI Agents - from Anthropic
Something big is happening
AI Cybersecurity Trends and Defense Strategies for 2026
Agent World Model
Catching AI Sleeper Agent - LLM Backdoors
AI 2026: Scaling Laws, China, and the Race for AGI
The Hidden Cost of AI: Is Automation Killing Your Skills?
How AI changes software engineering
The creator of Clawd - ship code without reading it.
Kimi 2.5 and Data Agent Swarms
Claude's constitution
The World after AGI - Dario Amodei and Demis Hasssabis
Future of AI & Global Economy - Nvidia CEO Jensen Huang and BlackRock's Larry Fink
Recursive LM - model solves context rot
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
DSPy: Programming and Optimizing LLM Workflows with Systems Mindsets
Based on Claude Agent SDK — Thariq Shihipar, Anthropic
Cybersecurity Trends in 2026: Shadow AI, Quantum & Deepfakes
DeepSeek: Manifold-Constrained Hyper-Connections (mHC)
AI agent trends 2026 - Google
Building reliable AI Agent with domain memory
METR's Benchmarks vs Economics: The AI capability measurement gap
Adaptation of Agentic AI
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
Career Advice in AI
Leadership in AI Assisted Engineering
AI Consulting in Practice
Google - 5 days: Prototype to Production
Google - 5 days: Agent Quality
Google - 5 days: Context Engineering: Sessions & Memory
The Gemini Interactions API
Google - 5 days: Agent Tools
Google 5 days: Introduction to Agent
The Adoption and Usage of AI Agents: Early Evidence from Perplexity
Monetizing AI: Pricing Strategies and Experimentation
The 2026 State of AI Agents in Production - report from Anthropic
Agents to Skills: Building Expertise with Procedural Knowledge
The Renaissance Developer - Dr. Werner at AWS re:Invent 2025
The RPI workflow (Research, Plan, Implement) - for advanced AI Coding Agent
The complete IDE workflow for AI-driven development - the BMAD method
Weaponizing AI: The Rise of Autonomous Cyber Attacks
MAKER: Million-Step LLM Tasks with Zero Errors
From Context Engineering to AI Agent Harnesses
First AI-Orchestrated Cyber Espionage Campaign Disrupted
Sam Altman on the future of AI and its massive impact on society
🧠 Supervised Reinforcement Learning for Step-wise Reasoning
Kimi K2: the current Leading Open-Weight Agentic Model
AI Vision of the Future: An Expert Panel Discussion
Creating Claude Code: Agent Design and Product Philosophy
Context Engineering 2.0: The Context of Context Engineering
⚡ Agent Lightning: Reinforcement Learning for Any AI Agent
🛡️ Breaking Agent Backbones: Evaluating LLM Security in AI Agents
🚀 OpenAI's Future: Research, Product, and Infrastructure Vision
GitHub Universe 2025: Agent HQ, The Agent Workflow
Jensen Huang - NVIDIA - Keynote 10/2025
Perplexity at Work: A Guide to Getting More Done
Context Engineering for AI Agents - from LangChain vs Manus
💻 A Survey of Vibe Coding with LLMs
AI Adoption, Productivity, and System Thinking - from the interview with Huyen Chip
The Hidden Dangers of Browsing AI Agents
🤏 DeepSeek-OCR: Contexts Optical Compression
Claude Skills: Standard Operating Procedures for Agents
Self-Adapting Language Models (SEAL)
Training-Free Group Relative Policy Optimization for LLM Agents
OpenAI's Vision: AGI, Sora, and Bottlenecks
Agentic Context Engineering: Evolving Contexts for LLMs
Less is More: Recursive Reasoning with Tiny Networks
Understanding the 4 Main Approaches to LLM Evaluation - from Sebastian Raschka
OpenAI DevDay 2025: Agents, Apps, and GPT-5 Pro
Self-Supervised Learning and the Future of AI - from a lecture given by Yann LeCun
Skill erosion, where relying on intelligent systems creates an "illusion of mastery" while core competence fades
The Essential Startup Guide to Building AI Agents with Google
LIMI: Less Is More for Intelligent Agency
AI Adoption: Claude and ChatGPT Usage Patterns
Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning
⚖️ Self-Consistency Improves Chain-of-Thought Reasoning in LMs
Economic Index Report by Anthropic - 09/2025: Uneven Global and Enterprise AI Adoption
🤔 How People Use ChatGPT - from OpenAI Report
LLM Interview Questions: A Comprehensive Guide
Sam Altman & Khosla Ventures - AI: Evolution, Disruption, and the Future of Work
Distilling Step-by-Step: Outperforming LLMs with Less Data
😵💫 Why Language Models Hallucinate
Attention Is All You Need
LoRA: Low-Rank Adaptation of Large Language Models
The Ultimate Guide to Fine-Tuning LLMs
Compressing Large Language Models
The Enterprise AI Divide: Adoption, Failure, and Future Trends
AI's Rapid Ascent: MacroHard, Meta's Midjourney, and Sentient Concerns
Task-in-Prompt (TIP) adversarial attacks
Prompt Engineering: Still Essential – The Comprehensive Guide to AI Mastery
Andrew NG: Building Faster Startups with AI
LightRAG: Graph-Enhanced Retrieval-Augmented Generation for LLMs
Large Language Models (LLMs) in Cybersecurity
Fine-Tuning Large Language Models
Foundations of Large Language Models
GPT-5: The Future of AI
Small Language Models are the Future of Agentic AI
Deep Agents: Architectures for Advanced AI Performance
The Relentless Vision of Dario Amodei and Anthropic
Perplexity CEO: AI's Impact on Search, Browsers, and Jobs
Context Engineering with the PRP Framework
How to build an AI Agent
Navigating the Superintelligence Race
Founding Groq and the Future of AI
AI's Watershed: June 2025 Breakthroughs
Context Engineering
Becoming an AI-First Company: A Strategic Guide - BOX White paper
Software's Evolution: From Code to AI Operating Systems - Andrej Karpathy
The Agent Development Life Cycle
Small vs. Large AI Models: Trade-offs and Use Cases
GenAI: Skills, Markets, and Models
Apple WWDC 2025: Intelligence, Design, and Evolution
The Prompt Engineering Handbook
Darwin Gödel Machine: Open-Ended AI Evolution
Master Claude Code - Practical Tips and Tricks
Andrew Ng: State of AI Agents
Sergey Brin on the Future of AI and Gemini
Google I/O '25 Developer Keynote
Code with Claude Opening Keynote
Google I/O 2025 AI Stage: Day 1 Highlights
Microsoft Build 25 Keynote
Google IO 25
Log Anomaly Detection with LogLLaMA and RL
CySecBERT: Domain-Adapted Language Model for Cybersecurity
GitHub Engineering Success Playbook
Building AI Agents with a 7-Node Blueprint
How AI Reinventing Software Business Models
Sequoia AI Ascent 2025: The Trillion-Dollar Opportunity
LSAST: LLM-Supported Static Application Security Testing
MCP versus API: AI Agent Integration
A Survey of AI Agent Protocols
Mem0: Scalable Long-Term Memory for AI Agents
The Art and Science of Vibe Coding
12 factor agents
The AI Scientist: Automated Scientific Discovery
Thinking About Agent Frameworks: A Comprehensive Guide
Google A2A: Protocol for Interoperable AI Agents
Scaling AI Use Cases: An Adoption Guide
AI in the Enterprise: Seven Lessons from Frontier Companies
Practical Guide to Building AI Agents
Lightweight KG Reasoning with Language Model Prompts
Agentic Knowledgeable Self-awareness for Language Model Agents
AI 2027: Preparing for Superintelligence
Chapter 5&6: All-In on AI - How Smart Companies Win Big with Artificial Intelligence
Chapter 3 and 4: All-In on AI - How Smart Companies Win Big with Artificial Intelligence
All-In on AI: How Smart Companies Win Big with Artificial Intelligence (chapter 1 & 2)
Google Cloud Next 2025: The New Way to Cloud
AI's Growing Role in Software Development and the Future of Work
AI Model and Security Developments: Amazon, Google, Meta, Microsoft
AI Agents: Use Cases, Integration, and Business Impact
Decoding AI Agents: Infrastructure, Frameworks, and Market Trends
LLM Security: Threats, Detection, and Mitigation Strategies
Operationalizing Generative AI with MLOps on Vertex AI
LLMs for Domain-Specific Problem Solving
Vibe Coding: Setup, Advanced Tips, and Tricks
Agents Companion: Building and Evaluating Generative AI Agents
Generative AI Agents: Architecture, Tools, and Implementation
Embeddings and Vector Stores: A Comprehensive Guide
The Art and Science of Prompt Engineering
Foundational Large Language Models and Text Generation
Claude 3.7 Sonnet: Usage Patterns and Economic Insights
Qwen2.5-Omni: An End-to-End Multimodal Model
Knowledge Graph Enhanced Software Repair
GitHub Copilot: Enhanced AI with Custom Instructions
Knowledge Workers and Large Language Models: Current and Future Use
Chain-of-Tools: Reasoning with Massive Unseen Tools
Claude 3.5 Sonnet Achieves New SWE-bench Verified State-of-the-Art
Transformers Without Normalization: Dynamic Tanh Achieves Strong Performance
Fin-R1: Financial Reasoning with a Lightweight Language Model
Claude's "Think" Tool: Enhanced Complex Problem Solving
The Past, Present, and Future of AI for Developers
LLM Concepts Explained: Sampling, Fine-tuning, Sharding, LoRA
NVIDIA GTC 2025 Keynote: AI Factories and Accelerated Computing
Agentic RAG: Intelligent Retrieval Augmented Generation
🎣 Phishing: Attacks and Top Cybersecurity Defense Strategies
RAG vs. CAG: Augmenting AI Model Knowledge
LONGREPS: Reasoning Path Supervision for Long-Context Language Models
Prompt Engineering for AI
GraphFC: Graph-based Fact-Checking with Claim Decomposition
LLM Agents: A Survey of Planning Approaches
Anthropic's Model Context Protocol (MCP): Origins, Functionality, and Impact
🐳 Dockerizing AI: Model Context Protocol with Claude Desktop
Model Context Protocol: A QA Guide for AI Testing
Graph RAG: A Query-Focused Summarization Approach
AI Agents: Tools, Planning, and Failure Modes - Huyen Chip
AI Agents Research Papers: Best of 2024
Fine-Tuning LLMs: A Deep Dive into Alternatives
Advanced Prompt Engineering Techniques
ChatGPT Prompts for Software Engineers
The Art of AI Prompt Crafting
Generative AI Agents: A Comprehensive Guide
The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
Building Effective LLMs Agents
Model Context Protocol (MCP) Explained
LazyGraphRAG: High-Quality, Low-Cost Graph-Enabled RAG
Retrieval Augmented Generation Architectures
Graph RAG: A Query-Focused Summarization Approach
DeepSeek-R1: Reasoning via Reinforcement LearningDeepSeek-R1: Reasoning via Reinforcement Learning
Google Cloud AI Business Trends 2025
LLM Post-Training: Reasoning, Reinforcement Learning, and Scaling