Vibe Coding Is The WORST IDEA Of 2025
Vibe coding might sound trendy, but in this video Dave Farley explains why vibe coding is one of the worst ideas in software engineering and software development in 2025. Discover what vibe coding really is, why it fails in real-world projects, and how relying on AI coding tools without proper engineering practices can lead to disaster. If you care about writing better code, improving your programming skills, and avoiding costly mistakes, you need to hear this. - Dave on X ➡️ https://x.com/davefarley77 Dave on LinkedIn ➡️ https://www.linkedin.com/in/dave-farley-a67927/ Dave on bluesky ➡️ https://bsky.app/profile/davefarley77.bsky.social Modern Software Engineering on X ➡️ https://x.com/ModernSoftwareX Modern Software Engineering on LinkedIn ➡️ https://www.linkedin.com/company/modern-software-engineering Modern Software Engineering on bluesky ➡️ https://bsky.app/profile/modernswe.bsky.social - ⭐ PATREON: Join the Continuous Delivery community and access extra perks & content! ➡️ https://bit.ly/ContinuousDeliveryPatreon 🎥 Join Us On TikTok ➡️ https://www.tiktok.com/@modern.s.engineering - CHANNEL SPONSORS: Equal Experts is a product software development consultancy with a network of over 1,000 experienced technology consultants globally. They increase the pace of innovation by using modern software engineering practices that embrace Continuous Delivery, Security, and Operability from the outset ➡️ https://bit.ly/3ASy8n0 TransFICC provides low-latency connectivity, automated trading workflows and e-trading systems for Fixed Income and Derivatives. TransFICC resolves the issue of market fragmentation by providing banks and asset managers with a unified low-latency, robust and scalable API, which provides connectivity to multiple trading venues while supporting numerous complex workflows across asset classes such as Rates and Credit Bonds, Repos, Mortgage-Backed Securities and Interest Rate Swaps ➡️ https://transficc.com - 👕 T-SHIRTS: A fan of the T-shirts I wear in my videos? Grab your own, at reduced prices EXCLUSIVE TO CONTINUOUS DELIVERY FOLLOWERS! Get money off the already reasonably priced t-shirts! 🔗 Check out their collection HERE: ➡️ https://bit.ly/3Uby9iA 🚨 DON'T FORGET TO USE THIS DISCOUNT CODE: ContinuousDelivery - BOOKS: 📖 Dave’s Book "Modern Software Engineering" is available as paperback, or kindle here ➡️ https://amzn.to/3DwdwT3 and NOW as an AUDIOBOOK available on iTunes, Amazon and Audible. 📖 The original, award-winning "Continuous Delivery" book by Dave Farley and Jez Humble ➡️ https://amzn.to/2WxRYmx 📖 "Continuous Delivery Pipelines" by Dave Farley Paperback ➡️ https://amzn.to/3gIULlA ebook version ➡️ https://leanpub.com/cd-pipelines 📖 "The Software Developers’ Guidebook Amazon ➡️ https://amzn.to/4f9ozFK ebook version ➡️ https://leanpub.com/softwaredevelopersguidebook NOTE: If you click on one of the Amazon Affiliate links and buy the book, Continuous Delivery Ltd. will get a small fee for the recommendation with NO increase in cost to you. - #vibecoding #aicoding #aidevelopment #softwareengineering #softwaredevelopment #programming
Video Chapters
- 0:00 Andrej Karpathy unveils the enigmatic concept of "vibe coding."
- 1:04 The "vibe coding" sensation: Is this viral idea a game-changer or a major misstep?
- 1:56 Decoding the real challenge: Why problem-solving, not just coding, defines success.
- 5:04 Beyond the "vibe": Why precision, not chatter, is the bedrock of programming.
- 6:54 The programmer's blueprint: Master these three essential goals for robust software.
- 9:53 The true test of code: Can your software gracefully adapt and evolve?
- 10:45 AI's arrival: Unmasking the fundamental challenges that persist in programming.
- 12:33 Navigating AI's blind spots: The critical role of version control and iterative fixes.
- 15:24 Engineering tomorrow: Moving from vague prompts to precise, executable specifications.
- 16:21 The final verdict: Why "vibe coding" falls short on core software engineering principles.
Original Output
0:00 Andrej Karpathy unveils the enigmatic concept of "vibe coding." 1:04 The "vibe coding" sensation: Is this viral idea a game-changer or a major misstep? 1:56 Decoding the real challenge: Why problem-solving, not just coding, defines success. 5:04 Beyond the "vibe": Why precision, not chatter, is the bedrock of programming. 6:54 The programmer's blueprint: Master these three essential goals for robust software. 9:53 The true test of code: Can your software gracefully adapt and evolve? 10:45 AI's arrival: Unmasking the fundamental challenges that persist in programming. 12:33 Navigating AI's blind spots: The critical role of version control and iterative fixes. 15:24 Engineering tomorrow: Moving from vague prompts to precise, executable specifications. 16:21 The final verdict: Why "vibe coding" falls short on core software engineering principles. Timestamps by StampBot 🤖
Unprocessed Timestamp Content
0:00 Andrej Karpathy introduces "vibe coding" with AI assistance. 0:11 Is "vibe coding" the worst software idea of the year? We'll see. 0:21 Analyzing Andrej Karpathy's legendary 1000-character "vibe coding" tweet. 0:41 Speaker suspects Karpathy's tweet about vibe coding might be pure sarcasm. 1:04 Vibe coding: contender for worst software idea, but it's gone viral. 1:40 The allure of chatting with an LLM for working code, but something's amiss. 1:56 Writing code isn't the tricky part, it's understanding the problem. 2:03 When non-technical folks and developers misinterpret coding's true challenge. 2:39 Defining a programmer by their tools, not their actual problem-solving prowess. 2:57 The true difficulty in software development doesn't lie in programming languages. 3:04 Re-evaluating Karpathy's "vibe coding" principles. Forget the code even exists. 3:11 The product owner just wants a solution, but the developer holds the keys. 3:30 Poor outcomes often occur when complex requests meet naive programming approaches. 3:43 Computers ultimately require precise, deterministic instructions to function correctly. 4:35 Comparing programming languages over decades: consistency in explicit detail reigns. 5:04 Programming languages: precise tools to structure our thinking, not vague human chatter. 5:57 Why "vibe coding" is not the correct solution for robust software development. 6:01 Legal documents: another example of natural language's struggle for ultimate precision. 6:17 Programming isn't just coding; it's like defining a plumber by their wrench. 6:54 The three critical goals of programming: organize thoughts, communicate, instruct computers. 7:46 Essential techniques for building good software: modularity, cohesion, managing coupling. 8:13 The persistent challenge: defining "good taste" in software design decisions. 9:00 Training data means LLMs will create both good and, well, less-good code. 9:53 Software quality is truly measured by our ability to confidently change it. 10:08 Rewriting code from scratch with AI: does it really make things easier to change? 10:45 The three core problems of programming, illuminated by AI's advent. 11:21 How human developers tackle complexity: compartmentalizing problems for change. 12:33 AI-generated code often ignores version control and round-tripping for corrections. 13:28 Engineering success depends on our ability to identify and fix mistakes reliably. 13:49 Can we trust AI to give us the same results every time, or will it "vibe out"? 14:22 Compartmentalizing changes is crucial, especially when AI starts rewriting everything. 15:24 The future of programming relies on executable specifications, not vague prompts. 16:00 Programming evolves from defining "how" to clearly specifying "what" we want. 16:21 "Vibe coding" simply misses the mark on fundamental software engineering challenges. Timestamps by StampBot 🤖