The Merge (by CodeRabbit)

CodeRabbit
  • 5.0 (1)
  • TECHNOLOGY

The Merge by CodeRabbit is a podcast that brings you deep conversations with legendary developers who've shaped the tools we use every day. We explore how artificial intelligence is transforming software development while celebrating the creators and tools that built our foundation. Each episode features intimate discussions about building developer tools, maintaining open source projects, and navigating the evolution of technology.

Episodes

  1. Why NVIDIA is Betting on Open Source and Ultra-Fast Inference

    APR 29

    Why NVIDIA is Betting on Open Source and Ultra-Fast Inference

    Chris Alexios joins Hendrik at our CodeRabbit Office in San Francisco to pull back the curtain on NVIDIA’s latest model family, Nemotron-3 (Nano, Super, and Ultra). They dive deep into the "Slop-pocalypse" of AI-generated code, the transition from being a syntax writer to a "High-Altitude Manager" of AI agents, and why open-source models are essential for Sovereign AI. Topics covered: - The "Faster is Smarter" Theory: Why iteration speed beats parameter count. - Context Engineering: Why the context window is a first-class infrastructure. - NVIDIA’s 5-Layer Cake: How hardware and software co-design creates the world’s fastest chips (Blackwell). - Vibe Coding vs. Real Engineering: Can AI agents actually solve the "Slop" problem in software? - Specialists vs. Generalists: Why the future looks like a swarm of specialized MoE models. [Timestamps]0:00 - Introduction: Faster Models = Smarter Models?2:45 - Meet Chris Alexios: From Bird Bots to NVIDIA5:30 - The Evolution of AI Engineering: Beyond the Rules8:45 - Why Context Engineering is the new Prompt Engineering12:15 - RAG Patterns: Do you actually need a Vector Database?18:30 - Codex vs. Claude: Choosing the right tool for the "Vibe"22:10 - Inside NVIDIA: Product Research Engineering & The 5-Layer Cake26:45 - Nemotron Explained: Nano, Super, and Ultra30:15 - The Capability Frontier: Why Evals are so Hard35:20 - Local AI & Quantization: Will GPT-5 fit on a phone?38:45 - Synthetic Data: Is data a fossil fuel or renewable energy?42:30 - Addressing AI Bias and the Importance of Open Models48:00 - The Future of Coding: Are we all just "Agent Managers" now? [Resources & Links]🔗 Follow Chris Alexios on LinkedIn: https://www.linkedin.com/in/csalexiuk/ #NVIDIA #AI #SoftwareEngineering #MachineLearning #Nemotron #LLMs #VibeCoding #Blackwell #TheMerge #AIProgramming

    56 min
  2. Claude OPUS 4.7 - Anthropic drops a new Model - David Loker (VP of AI at CodeRabbit)

    APR 16

    Claude OPUS 4.7 - Anthropic drops a new Model - David Loker (VP of AI at CodeRabbit)

    The Merge (by CodeRabbit)

    21 min
  3. Most Founders Don't Understand Open Source | Ivan Burazin (CEO, Daytona)

    APR 13

    Most Founders Don't Understand Open Source | Ivan Burazin (CEO, Daytona)

    Most Founders Don't Understand Open Source | Ivan Dzido (Daytona) "Most people actually don't understand what they are signing off to...". In this episode of The Merge, we sit down with Ivan Dzido, CEO of Daytona, to discuss why the traditional "sandbox" is dead and why AI agents need "composable computers" instead. Ivan reveals how Daytona spins up environments in just 60 milliseconds—including network latency—which is literally half the time it takes a human to blink. We also dive into his $24M Series A, the 15-year history of his founding team, and why he believes the CLI might be a bottleneck for AI productivity. Explore Daytona: https://www.daytona.io What You Will Learn: The 60ms Breakthrough: Why speed is the ultimate primitive for the next generation of AI agents.Composable Computers vs. Sandboxes: Why an agent needs a full, stateful environment, not just a temporary code execution box.The Open Source Myth: Ivan’s "unpopular opinion" on why founders are picking the wrong licenses and how Daytona uses AGPL to protect their business.Viral Marketing in DevTools: The story behind the "Run AI Code" shirts that took over San Francisco.Timestamps: 00:00 – The 60ms "Blink of an Eye" Speed 01:05 – Welcome to Episode 5 of The Merge by CodeRabbit 02:01 – What is a Composable Computer? 05:05 – 15 Years in the Making: The History of the Daytona Team 08:53 – Starting 12 Years Ahead of GitHub Codespaces 10:40 – Why Every Knowledge Worker Needs an Agent Computer 13:16 – The "Compute" Conference at Chase Center 16:43 – How to Create Viral Tech Swag (The New Relic Strategy) 19:32 – Three Main Use Cases for AI Sandboxes 23:14 – The Technical Deep Dive: How Daytona Works Under the Hood 30:00 – Why Daytona Chose the AGPL License 34:55 – Advice for Open Source Founders: "Lightning Must Strike Twice" 39:04 – Rapid Fire: Favorite IDEs, Licenses, and Languages  Connect with Us: CodeRabbit (The Host): https://coderabbit.aiDaytona GitHub: https://github.com/daytonaio/daytona Compute Conference: https://compute.daytona.io Don't forget to LIKE and SUBSCRIBE for more deep dives into the future of AI infrastructure! #AI #OpenSource #DevTools #Daytona #CodeRabbit #SoftwareEngineering #AIAgents

    45 min
  4. TypeScript BEATS Python when building AI Agents (Mastra's YC Journey)

    MAR 24

    TypeScript BEATS Python when building AI Agents (Mastra's YC Journey)

    Is the era of Python-only AI over? Mastra CTO Abhi Aiyer breaks down why 1.2 million developers are shifting to TypeScript to build production-ready AI agents, the brutal realities of Y Combinator, and why the "let AI code while you go to the bar" myth is complete BS. [Main Description]We’ve always been taught: If you want to build AI, you learn Python. But as the ecosystem shifts from training models to building functional, production-ready AI Agents, the requirements are changing rapidly. In this episode of The Merge, we sit down with Abhi Aiyer, Co-founder and CTO of Mastra (YC W25), to unpack the wild journey of building one of the fastest-growing open-source AI frameworks. We cover their pivotal rewrite at the Crafty Fox Ale House, the struggle of having zero users at the start of YC, and their brilliant "pocket-sized book" marketing tactic that took over San Francisco. If you are a web developer, an open-source maintainer, or just trying to figure out how to actually deploy AI agents in production—this is a masterclass you don't want to miss. 🎙️ In this episode, we cover: Why "Python trains, but TypeScript ships." The reality of YC: What happens when you get in, but nobody uses your product. How Mastra scaled to over 1.2 MILLION monthly downloads. The truth about multi-agent workflows and the "CloudBot" hype. The commercial open-source playbook: How to monetize and manage 100+ maintainers using CodeRabbit. ⏱️ Timestamps:0:00 - The "Go To The Bar" AI Coding Myth1:25 - Welcome Abhi Aiyer: The Origins of Mastra4:40 - LangChain Frustrations & The Need for TypeScript7:15 - The NextConf Pivot & The Crafty Fox Ale House Rewrite10:30 - The Y Combinator (YC W25) Experience & Early Struggles14:50 - The Viral Pocket-Sized AI Agent Book Strategy18:15 - Python vs. TypeScript: Why TS is Winning the Agent War24:30 - Moving AI Docs into the Modules (MCP Innovation)28:40 - How to Make an Open-Source Company Profitable33:20 - Managing a Massive OSS Community (Shoutout CodeRabbit!)40:15 - Real-World Multi-Agent Workflows & Future Predictions45:30 - Rapid Fire Questions 🔗 Links & Resources: Check out Mastra: https://mastra.ai Follow Abhi Aiyer on X: https://x.com/abhiaiyer Automate your code reviews with CodeRabbit: www.coderabbit.ai 👇 Join the Conversation:Which side are you on? Are you building your AI agents in Python or TypeScript? Let us know in the comments! #AIAgents #TypeScript #Python #SoftwareEngineering #YCombinator #OpenSource #WebDevelopment #Mastra #TechPodcast #CodeRabbit

    47 min
  5. DID GOOGLE JUST WIN THE AI RACE?

    MAR 16

    DID GOOGLE JUST WIN THE AI RACE?

    Is the "Benchmark Chasing" era over? With the release of Gemini 3.1 Pro and the specialized Deep Think mode, Google isn't just releasing a faster model—they are introducing a fundamental shift in machine reasoning for real-world developer workflows. In this episode of The Merge AI Newsroom, live from CodeRabbit’s San Francisco studio, applied AI expert Erfan Al-Hossami (ex-Stability AI, LLM researcher) breaks down why this is Google’s most significant release of 2026. What we cover in this episode:     The ARC-AGI-2 Breakthrough: Why a 77.1% verified score (and Deep Think hitting ~85%) is the first credible proof of fluid intelligence.     Developer Workflow Shifts: Why task definition and problem framing now matter more than raw syntax coding.     Benchmark Deep Dive: Massive leaps on Humanity’s Last Exam, SWE-Bench Verified, Terminal-Bench, and Codeforces.     Model Strategy: Deep Think vs. Gemini 3.1 Pro—when to use which, plus a breakdown of cost vs. performance trade-offs.     The Future of Agents: Real-world implications for autonomous code review, debugging, and agentic task execution. Timestamps:00:00 - Intro: Why Gemini 3.1 Pro feels different01:41 - ARC-AGI-2 Explained: The most credible AGI benchmark03:42 - Deep Think vs. Gemini 3.1 Pro: Architecture & UI differences05:00 - The 2026 Benchmark Gauntlet (SWE-Bench, HLE, & more)08:40 - Impact on Developers: How your daily workflow changes15:16 - Context Window Tips & Custom Thinking Controls19:34 - Token Economics: Model selection & cost strategy21:19 - What’s next for Google DeepMind + Final Thoughts Watch the full conversation with Erfan Al-Hossami now 👇 🔗 Join the CodeRabbit Community:→ Website: https://coderabbit.ai About The Merge: The Merge AI Newsroom provides expert AI analysis with zero hype. We go beyond the headlines to show you how frontier models actually perform in production environments. #Gemini31Pro #DeepThink #GoogleAI #ARCAGI #TheMerge #CodeRabbit #AICoding #ArtificialIntelligence #AIBenchmarks #SoftwareEngineering2026

    21 min
  6. From Psychologist to 12k Stars on Github: The Career Pivot You Need to Hear About!

    MAR 16

    From Psychologist to 12k Stars on Github: The Career Pivot You Need to Hear About!

    🎙️ The Merge Episode #2: From Psychology to 12,000 Stars with Herrington Darkhome In this episode of The Merge, Hendrik sits down with Herrington Darkhome, the creator of ast-grep, a lightning-fast structural search and rewriting tool written in Rust. Discover how a self-taught programmer with a background in cognitive psychology went from discovering Vim on a Chromebook to becoming a core maintainer for Vue.js and building a tool used by tech giants like Microsoft and Amazon. We dive deep into why Regular Expressions (Regex) fail for large-scale codebases, how Abstract Syntax Trees (AST) are the secret to "ground truth" for AI agents, and why Harrington believes the "open source for love" myth needs to die. 🔍 Inside This Episode: Structural Search vs. Regex: Why treating code as a tree is more precise than treating it as a sequence of characters.The Rust Advantage: How ast-grep achieves blazing-fast performance and stable concurrency.AI & Open Source in 2026: Why human communication and intent are more important than just writing code in the AI era.Scaling Knowledge: Using linting as a way to dynamically inject team knowledge into AI agent contexts.Monetizing Open Source: The reality of building sustainable, "serious" projects in today's ecosystem. 🚀 Level Up Your Code Review This podcast is brought to you by Code Rabbit, the AI-first code review platform that uses tools like ast-grep to ensure high-fidelity, context-aware reviews. Try Code Rabbit for Free: https://coderabbit.ai/Star ast-grep on GitHub: https://github.com/ast-grep/ast-grep🛠️ Resources & Links: ast-grep Official Website: https://ast-grep.github.io/Follow Code Rabbit on Twitter/X: @CodeRabbitAIJoin the Discord: (Link found in ast-grep's official docs)Enjoyed the episode? Support the show by Subscribing and hitting the Bell Icon 🔔 to stay updated on the latest in open source and AI. #OpenSource #RustLang #ASTGrep #CodeReview #AIAgents #SoftwareEngineering #TheMergePodcast

    48 min
  7. GPT-5.3-Codex vs. Claude Opus 4.6 Comparison: Performance, Benchmarks & Agentic Coding Workflows

    FEB 11

    GPT-5.3-Codex vs. Claude Opus 4.6 Comparison: Performance, Benchmarks & Agentic Coding Workflows

    THE MERGE - AI NEWSROOMGPT-5.3-Codex vs. Claude Opus 4.6: Benchmarks and Best Agentic Workflows OpenAI and Anthropic just changed the game for February 2026. But as these models get more "agentic," the stakes for code quality have never been higher. Today on the AI Newsroom, we’re pitting GPT-5.3-Codex against Claude Opus 4.6 to see which model actually earns its keep in a production monorepo. We’re moving beyond simple autocomplete into the era of "Code Review as the New Coding." We break down the latest benchmarks (SWE-Bench Pro & Terminal-Bench 2.0) and reveal how CodeRabbit’s own internal metrics show a 1.7x increase in defects when AI-generated code isn't properly validated. WHAT WE COVERED: GPT-5.3-Codex: Why it’s the "Founding Engineer" of models (speed, iteration, and CLI mastery). Claude Opus 4.6: The "Senior Architect" approach—handling 1M token refactors without losing the thread. The CodeRabbit Eval: How we benchmarked these models on signal-to-noise ratio and bug detection. Agentic Workflows: Parallel "Agent Teams" vs. Hierarchical Orchestration. 🕒 TIMESTAMPS: 0:00 - The Feb 2026 AI Collision 1:45 - GPT-5.3-Codex: 77.3% on Terminal-Bench 2.0 4:10 - Opus 4.6: Why a 1M Token Context window changes refactoring 6:30 - The "AI Code Crisis": 1.7x more defects in AI PRs? 9:15 - CodeRabbit Metrics: Precision vs. Noise in GPT-5.3 12:00 - Pricing Breakdown: $5 vs $25 - The "Intelligence Tax" 14:40 - Pro-Tips: High-context prompting for Senior Devs 17:05 - The Future of Code Review in 2026 💡 KEY TAKEAWAY: GPT-5.3 is built to DO, while Opus 4.6 is built to THINK. At CodeRabbit, we use both, but we always treat their output as a "draft" that requires agentic validation. 🔗 LINKS & RESOURCES: Our Latest Report: State of AI vs. Human Code Generation 2026 [ https://www.coderabbit.ai/blog/state-of-ai-vs-human-code-generation-report ] Sign up for free! https://www.coderabbit.ai/ Join our Discord: https://discord.gg/coderabbit #CodeRabbit #AINewsroom #GPT5 #ClaudeOpus #AgenticCoding #SoftwareEngineering #CodeReview #AI2026

    17 min
  8. After 2025: What’s Next for AI Coding in 2026 - The Merge (by CodeRabbit) - Episode1

    JAN 23

    After 2025: What’s Next for AI Coding in 2026 - The Merge (by CodeRabbit) - Episode1

    2025 was chaos in the best way: DeepSeek cracked open the model monopoly and proved world-class open weights don't need infinite budgets. Vibe coding went mainstream - prompt your way to an app without staring at code - unlocking ideas for non-engineers but flooding repos with bugs (our data shows AI code spawns ~1.7× more issues than human-written). Agents evolved from demos to long-running beasts, CLI tools like Claude Code let AI run wild in terminals, Cursor/Windsurf supercharged IDEs for pros, Gemini 3 stormed back with killer reasoning, Anthropic scooped Bun, and MCP + Agent Skills started standardizing the agent wars. Hosted by Hendrik (CodeRabbit Dev Advocate) with David Loker (VP of AI), we dissect the timeline, the hype vs. reality, and why blind vibe coding is creating a maintenance nightmare. David drops hard truths and real predictions on 2026...  Try CodeRabbit: https://www.coderabbit.aiBlog: https://www.coderabbit.ai/blogJoin our Discord: https://discord.gg/coderabbit Subscribe and drop topics you want us to test next.

    34 min

  9. 11/26/2024

    Building iTerm2, the Popular Mac Terminal: George Nachman on Dev Tools in the AI Era | Main AI

    Click here to view the episode transcript.

    31 min
  • 9 Episodes

Ratings & Reviews

About

The Merge by CodeRabbit is a podcast that brings you deep conversations with legendary developers who've shaped the tools we use every day. We explore how artificial intelligence is transforming software development while celebrating the creators and tools that built our foundation. Each episode features intimate discussions about building developer tools, maintaining open source projects, and navigating the evolution of technology.

Information

  • Creator
    CodeRabbit
  • Years Active
    2024 - 2026
  • Episodes
    9
  • Rating
    Clean
  • Copyright
    © 2026 CodeRabbit
  • Show Website
    The Merge (by CodeRabbit)

You Might Also Like