AI Engineering Podcast Summaries
AI Engineering on Yedapo: 41 summarized podcast and YouTube episodes. Each includes key takeaways, core concepts and notable quotes with timestamps.
Anthropic's New Rules Break Most Claude Code Setups
Eric Tech
Jul 29, 2026
Context bloat in Claude Code leads to token waste and instruction collisions, degrading model performance. By utilizing the '/doctor' command to prune unused skills and refine system prompts, users can significantly improve accuracy and efficiency for Claude 5 models.
Key insight: Anthropic's team successfully deleted over 80% of their system prompts for Opus 5 and Sonnet 5 models with zero loss in coding evaluation performance, proving that less is often more.
Learn AI Engineering in 2026 | Build a Full Stack AI Websites with Agents
JavaScript Mastery
Jul 17, 2026
Stop struggling with long, manual AI prompts. By defining a clear 'Agentic Engineering' workflow and project-specific skills, you can empower AI to draft its own implementation plans, which you simply review and approve. This approach enables the rapid development of sophisticated, production-ready applications like an AI-powered news aggregator.
Key insight: The most effective way to manage AI complexity is to stop writing long, exhaustive prompts and instead create an 'agents.md' file that defines your project's process, allowing the AI to generate its own specific implementation prompts for every task.
How To Build Your Own RAG AI System - Better Results Than Claude
Web Dev Simplified
Jul 14, 2026
This episode provides a comprehensive master class on building an automated RAG (Retrieval-Augmented Generation) system. It demonstrates a production-focused workflow using Next.js, Vercel Workflows for durable background ingestion, and Neon for vectorized storage.
Key insight: Using Vercel Workflows ensures long-running AI tasks and data ingestion processes are durable, enabling automated retries if a task fails halfway through.
FORGET Loop Engineering. Agentic Engineering is about THIS
IndyDevDan
Jul 13, 2026
The term 'loop engineering' obscures the reality of building scalable AI systems. Engineers must treat AI as one component in a trio of value creation: agents, code, and human oversight. By building 'software factories' that orchestrate these actors into deterministic workflows, engineers can achieve reliable, repeatable, and scalable production-grade outcomes.
Key insight: Code is the most reliable actor in an agentic system because it runs consistently at zero token cost and at the speed of light; never over-leverage LLMs when deterministic code can handle the task.
GPT 5.6 is here.. can we stop reading code now?
NeetCode
Jul 9, 2026
The rise of advanced models like Fable and GPT 5.6 has reignited the debate over whether developers should read generated code. While high-level architecture design and delegation are increasingly automated, the inherent non-determinism of LLMs makes hands-on technical oversight essential for long-term maintainability and performance.
Key insight: LLMs can produce vast amounts of code instantly, but they frequently lack architectural foresight, often choosing to duplicate functions rather than creating reusable components—a trap that only developers with actual implementation knowledge can avoid.
Building the most AI-pilled engineering team in the world | Fiona Fung (Manager of the Claude Code and Cowork Teams)
Lenny's Podcast: Product | Career | Growth
Jun 21, 2026
Software engineering has fundamentally shifted from manual code creation to high-velocity AI-assisted building. Leaders must now prioritize verification, system architecture, and cultivating high-agency teams while managing the new risks of async agent-based development.
Key insight: Anthropic engineers are now pushing eight times as much code per quarter as they were just a few years ago.
Matt Pocock’s Agentic Engineering Workflow (just copy him)
David Ondrej
Jun 18, 2026
The real competitive advantage in software development isn't the AI model itself, but the 'harness'—the environment and strategic architecture you build around it. By focusing on strategic programming and well-scoped delegation, developers can turn AI into a force multiplier, moving from tactical code-writing to high-level system orchestration.
Key insight: The most effective way to optimize token spend and performance is not by tweaking prompts, but by improving your codebase architecture so that even a 'stupider' or cheaper model can navigate and modify it effectively.
Do THIS Instead of watching endless AI Engineer Roadmaps (DataCamp Review)
Tech With Tim
Jun 15, 2026
AI engineering is shifting from theoretical research to practical application. This episode provides an honest review of a structured curriculum for software developers to master LLMs, RAG pipelines, and vector databases in 2026.
Key insight: You don't need a deep background in advanced mathematics or machine learning theory to be a successful AI engineer; the role is now primarily about integrating existing pre-trained models into business applications.
LAUNCHING COURSE AI POWERED APPS FUNDAMENTALS di @WPUCOURSE 🥳
WPU
Jun 7, 2026
The team argues that true mastery of AI-powered applications requires moving beyond superficial 'vibe coding' or automated prompts. By building apps that integrate AI at the architectural level—using technologies like Next.js, PGVector, and Gemini 3.5—developers can create intelligent systems that handle real-world tasks like financial analysis and multimodal data processing effectively.
Key insight: AI can be made significantly more powerful by using Retrieval Augmented Generation (RAG) and Agentic Workflows, which allow the model to reason through multi-step tasks independently rather than just generating static text.
PERSIAPAN LIVE LAUNCHING AI POWERED APPS FUNDAMENTALS di @WPUCOURSE
WPU
Jun 5, 2026
The team behind WPU Course reveals a new AI-focused curriculum that emphasizes foundational coding over superficial 'vibe coding'. By mastering AI-native integration, students learn to build functional applications that leverage AI models for real-world tasks, ensuring they understand the underlying mechanics rather than relying blindly on generated code.
Key insight: The instructors highlight that AI-driven development currently suffers from a 'token efficiency' problem; users often waste resources by failing to understand context management, leading to unnecessarily expensive and non-performant application architectures.
Los cursos de Ingeniería de IA que yo haría en 2026
midudev
Jun 3, 2026
La verdadera ingeniería de IA en 2026 trasciende el uso básico de prompts y APIs. El éxito reside en integrar agentes, RAG y fine-tuning dentro de flujos de trabajo reales, equilibrando la teoría con la práctica constante. Los desarrolladores deben evitar los cursos superficiales y enfocarse en rutas estructuradas que validen habilidades técnicas aplicables.
Key insight: La certificación AWS Certified AI Practitioner es un complemento estratégico indispensable para cualquier desarrollador, ya que valida conocimientos de IA generativa y servicios en la nube en un mercado altamente demandado.
AI engineer salary - What to expect: Junior to senior
Tech With Tim
May 27, 2026
AI engineering salaries have exploded, with junior roles often outperforming traditional director-level positions. This analysis breaks down compensation tiers, the critical shift from theoretical machine learning to production-ready deployment, and the specific skills driving the highest market premiums in 2025.
Key insight: Junior AI engineers in North America averaged $173,500 in total compensation in 2025, a figure that actually exceeds some director-level averages of $152,000 at comparable companies.
Complete Claude Code Course In 2 Hours For Developers
Krish Naik
May 25, 2026
Krishna demonstrates how to leverage the Claude Code ecosystem to transform software development through agentic workflows. By integrating custom sub-agents, skills, and plugins into your local environment, developers can automate complex tasks, perform codebase analysis, and execute parallel operations, significantly reducing manual effort while maintaining human-in-the-loop control.
Key insight: You can treat your terminal as a team manager by utilizing Agent Views to run multiple independent agentic sessions in parallel, each with its own context, memory, and specialized toolset.
Stop Vibe Coding Apps - Do this instead!
CodeWithHarry
May 25, 2026
Dhaval Patel argues that pure coding skills are reaching a dead end. To thrive, engineers must move beyond the 'vibe coding' trap, focusing on business ROI, robust system architecture, and human-in-the-loop validation. AI is a tool, not a replacement; real value lies in building scalable, reliable solutions, not just prototypes.
Key insight: Dhaval reveals that despite the hype, many 'AI projects' fail because they use a sledgehammer—large language models—where a simple statistical or rule-based approach would be cheaper, faster, and more accurate.
Burn through the backlog from hell with /triage
Matt Pocock
May 7, 2026
Effective AI agent workflows require structured task management to prevent inefficiency. By implementing a state-machine based 'Triage' skill, developers can transform chaotic GitHub issues into actionable, high-quality briefs that AI agents can execute autonomously.
Key insight: Managing AI agents is primarily a queue management problem; the 'ready for agent' label acts as a vital gatekeeping mechanism to prevent AI from attempting low-quality or out-of-scope tasks.
I reviewed 20 AI engineering courses, here are my top 5
Tech With Tim
May 1, 2026
Mastering AI engineering requires shifting focus from theoretical model research to practical, production-grade application development. This guide evaluates the top five training resources based on their interactivity, depth, and suitability for developers versus data scientists.
Key insight: AI engineering is not about building models from scratch but about utilizing pre-trained APIs, agents, and LLMOps to ship production-ready software efficiently.
Do THIS instead of watching endless tutorials — how to learn Python for AI
Tech With Tim
Apr 26, 2026
Most aspiring AI engineers stall by endlessly consuming tutorials without writing code. This guide provides a minimal, high-impact roadmap to learning Python by building, rather than just watching, ensuring you reach job-ready competency faster by focusing on practical, project-based application.
Key insight: For every hour spent watching educational content, you must spend at least an hour writing your own code to ensure actual retention of the material.
8 Claude Code Skills Every Developer Needs in 2026
Eric Tech
Apr 24, 2026
Out-of-the-box AI generates fragile, buggy code through chaotic "vibe coding." Former Amazon engineer Eric reveals how developers force Claude to adopt strict Test-Driven Development methodologies. By integrating custom skills, you transform a basic chat interface into an autonomous engineering team that brainstorms, tests, and deploys full features.
Key insight: You can completely bypass expensive vector databases and embeddings by using a basic Obsidian folder to give Claude an infrastructure-free RAG system.
Anthropic Finally Fixed The 1M Context Window Problem
AI LABS
Apr 22, 2026
Anthropic's massive one-million token context window creates a hidden trap called context rot, destroying Claude's reasoning long before capacity. The host reveals how Anthropic engineers like Tariq actively prevent this degradation. You must abandon default auto-compaction and adopt structured state-saving to keep your autonomous agents sharp.
Key insight: Claude's performance actually begins rotting at just 300,000 tokens—a mere 40% of its capacity—meaning the widely used auto-compaction feature often deletes critical project context entirely.
Lessons from 15,031 hours of coding live on Twitch with Chris Griffing [Podcast #214]
freeCodeCamp.org
Apr 3, 2026
Chris Griffin argues that server-side rendering is a bloated niche, yet developers treat it like a universal requirement. He reveals why over-reliance on AI "vibe coding" erodes the deep debugging skills necessary to save a product when it inevitably breaks. True mastery comes from the "saddle time" of building in public where every failure is an asset.
Key insight: Management never takes on extra work; just as SQL didn't replace database admins, AI won't eliminate developers—it just exposes those who can't debug their own prompts.
18 Claude Code Token Hacks in 18 Minutes
Nate Herk | AI Automation
Apr 2, 2026
Your Claude Code session isn't just getting longer; it’s becoming exponentially more expensive with every reply. By re-reading the entire history on every turn, 98.5% of your tokens are wasted on noise rather than new code.
Key insight: One developer tracked a 100+ message session and discovered that nearly 99% of the total token spend was purely for re-reading old chat history.
AI-Assisted Coding Tutorial – OpenClaw, GitHub Copilot, Claude Code, CodeRabbit, Gemini CLI
freeCodeCamp.org
Mar 31, 2026
Senior developers are unlocking extreme productivity by moving beyond basic chat prompts to full-scale AI orchestration. Bo KS reveals how to leverage tools like GitHub Copilot and Code Rabbit to automate the entire coding lifecycle from generation to security review. The secret isn't just the AI—it's the human-led architectural framework that prevents hallucination.
Key insight: Code Rabbit recently ranked #1 in the independent "Code Review Bench," outperforming Gemini and Claude by successfully balancing critical bug detection with minimal false positives across 300,000 pull requests.
I Used To Vibe Code All My Vue Apps Until I Found This
Program With Erik
Mar 30, 2026
Vibe coding often fails to deliver complex features, leading to endless prompt cycles and frustration. Spec-driven development forces AI agents to architect, define requirements, and create tasks before writing code, ensuring precision in large-scale projects.
Key insight: "Spec mode" generates formal architecture and "correctness properties"—automated tests that validate logic before any implementation begins.
343: הדרך שלנו לקוד שנכתב כולו באמצעות אייג׳טים
Startup for Startup
Mar 30, 2026
המהפכה האמיתית ב-Engineering אינה מסתכמת ב'עוזר כתיבה', אלא במעבר מוחלט לאג'נטים אוטונומיים שמנהלים משימות מקצה לקצה. דור כהן וניצן עזרה חושפים כיצד מהנדסי תוכנה הופכים ממבצעים למנהלי אסטרטגיה, כשצוואר הבקבוק עובר ממהירות המקלדת ליכולת האפיון והחשיבה המוצרית.
Key insight: היעד האסטרטגי של Monday.com הוא ש-100% מהקוד בארגון ייכתב על ידי אג'נטים, כשהמפתחים מתרכזים בבניית הלוגיקה והסביבה שמאפשרת ל-AI לקבל החלטות עצמאיות.
What happens when the model CAN'T fix it? Interview w/ software engineer Landon Gray [Podcast #213]
freeCodeCamp.org
Mar 27, 2026
Landon Gray argues that in the era of AI, individual developers must stop competing for commodity roles and start building a specialized reputation. By curating a unique perspective and leveraging a supportive professional community, engineers can move from cold-applying for jobs to having high-quality opportunities come to them.
Key insight: Isolation is dangerous in a career; you cannot effectively build your craft or identify your market value in a vacuum.
12 Hidden Settings To Enable In Your Claude Code Setup
AI LABS
Mar 25, 2026
Most developers struggle with Claude's 30,000-character output limit and one-month memory cap without realizing the fixes are hidden in obscure config files. By overriding default truncation and compacting behaviors, you can force the agent to process massive codebases and strictly adhere to your preferred libraries.
Key insight: Claude Code silently stops reading files after 2,000 lines without notifying the user; you must configure a specific hook using line-count offsets to bypass this hardcoded restriction.
How to Become an AI Engineer Fast
Tech With Tim
Mar 20, 2026
Tim reveals that breaking into AI engineering isn't about mastering complex research math, but mastering API orchestration and RAG. He argues that the real industry value lies in LLM Ops—managing rate limits and costs—rather than just building surface-level demos.
Key insight: Passive learning like watching tutorials only yields 20% retention, while active coding jumps that figure to a staggering 90%.
I Asked GPT-5 to Rebuild My 100K Line App. Its First Move Changed Everything.
Matt Maher
Mar 15, 2026
Modern software suffers from 'intent decay,' where the core business logic becomes inseparable from its UI. By tasking AI with a massive refactoring project, we reveal that frontier models can now surgically decouple logic from expression, though their reasoning strategies—ranging from exhaustive validation to rapid, surgical execution—differ profoundly.
Key insight: The AI independently decided to build three radically different, non-production user interfaces specifically to prove that it had successfully separated the application logic from the UI shell.
Dropbox uses Cursor to index over 550,000 files and build an AI-native SDLC
Cursor
Jan 26, 2026
Ali Dastan reveals why hesitation in the AI era is a terminal risk for software companies. By redesigning the entire development pipeline around agentic workflows, Dropbox has transformed engineering from a manual grind into a high-velocity system where even designers ship functional code.
Key insight: Dropbox now accepts over 1 million lines of agent-generated code every month, leveraging AI to handle everything from complex legacy migrations to instant bug fixes via screenshots.
How I use LLMs
Andrej Karpathy
Feb 27, 2025
Andrej Karpathy demystifies large language models by framing them as 'lossy zip files' of the internet. He demonstrates that moving beyond basic chat requires understanding context windows, tool use, and the shift toward 'thinking models' that leverage reinforcement learning to solve complex reasoning tasks.
Key insight: Karpathy reveals that LLMs are not inherently 'smart' but are probabilistic token-prediction engines; he treats them as a 'Council of Models' to cross-reference answers, acknowledging that even advanced models can hallucinate and require human verification.
