✨ What Is Vibe Coding?

Vibe coding = sit back and let your AI do the heavy lifting? Plus, the latest generative AI updates: Gemma 3 pushes multimodal AI forward, Emotionally Intelligent CVI brings lifelike video, Autonomous Agent Manus automates complex tasks, and more!

Hey there!

Vibe coding is the new trend these days spawning its own meme culture. Andrej Karpathy, the ex- Tesla AI lead and OpenAI founding member, recently coined the term to describe how large language models (LLMs) are getting so good that devs can simply "give in to the vibes" and allow LLMs to handle most of the coding.

Vibe coding already got into real businesses. Y Combinator mentioned that nearly a quarter of the code in their latest startup batch is almost entirely AI-generated. Founders are witnessing dramatic speed improvements: one founder from TrainLoop reported a leap from a 10× improvement to a staggering 100× increase in code generation speed within just one month.

A particularly striking example comes from @levelsio, who broke new ground by creating a fully AI-generated game using only two tools Cursor and Anthropic 's Claude. The project soared from $0 to $1 million in annual recurring revenue (ARR) in only 17 days, selling ad placements and amassing a user base of 320,000 players.

What Exactly Is "Vibe Coding"?

The roots of vibe coding trace back to early advancements in AI coding assistants. By late 2022, tools such as OpenAI 's Codex and GitHub Copilot had already begun generating useful code snippets from natural language prompts. In 2023, Karpathy famously predicted that "the hottest new programming language is English," hinting at a future where high-level prompts might replace traditional, low-level coding.

In essence, vibe coding means using AI as your co-pilot, or more of a primary coder, while you provide the guiding vision. As Karpathy puts it, "It's not really coding—I just see stuff, say stuff, run stuff, and copy paste stuff, and it mostly works."

In his own words, he describes a workflow where he talks to a coding assistant like Claude Composer (powered by Anthropic's Claude Sonnet) and SuperWhisper, issuing simple commands such as "decrease the padding on the sidebar by half." and let the AI output those code changes, and simply click "Accept All" without even reading diffs or understanding every line.

Karpathy's candid reflections on this workflow can be seen in his tweet here and in a follow-up tweet detailing his process here, which garnered an ambiguous "Hmm" reaction from Elon Musk .

The important nuance here is how much understanding the human maintains. Benj Edwards , Ars Technica 's Senior AI Reporter, made a great point on a distinction between using AI as an assistant and vibe coding highlighted by AI researcher Simon Willison .

Here's the gist:

• If you carefully review, test, and understand all the AI-written code, that's just using an LLM as an assistant, not vibe coding.
• True vibe coding implies a level of trust (or risk) where you accept code without fully understanding it. It's coding on autopilot: extremely fast and flexible, but a bit "loose" on the rigorous comprehension side.

Vibe Coding Impact: Shifting Roles and Business Dynamics

The concept of vibe coding is becoming increasingly intertwined with broader trends in AI, startup culture, and modern software development. We analyzed insights from Andrew Chen , General Partner at Andreessen Horowitz (read his take), along with key takeaways from a recent YC panel discussion (watch here).

Here's a condensed look at the biggest shifts impacting businesses, developers, and users:

• For business: As AI-generated code becomes more reliable, startups can drastically reduce their time-to-market and shorten product iteration cycles.
• For users: With more accessible and intuitive AI tools, even non-traditional developers like young enthusiasts or self-taught programmers can now build functional applications.

Robert Keus , Social Entrepreneur at Brthrs AI and GreenPT, shared that both of his daughters (8 & 11) have built their own webshops using Lovable , selling their handmade jewelry online. 👇🏼

• For developers: You are now expected to focus more on product sense rather than on writing code line by line. The traditional coding interview is losing relevance. Instead, companies are likely to prioritize a candidate's ability to use AI tools effectively, assess the quality of AI-generated code, and demonstrate strong product-thinking skills.

Something to keep in mind: While the promise of exponential productivity gains is enticing, current AI tools still fall short when it comes to debugging complex issues. Developers often find themselves "spoon-feeding" these systems explicit instructions to iron out errors, a process impossible without human oversight and deep technical expertise.

The development process is likely to bifurcate into two phases:

• Zero-to-one: Rapid feature shipping enabled by AI-generated code.
• One-to-n: Scaling, refining, and checking system robustness

Striking the right balance between embracing AI's potential and maintaining rigorous quality standards will be key to navigating AI integration in software development and other industries.

Now, let's get to the news!

Get the full details—read this newsletter on our website »

Updates on Generative AI Tools

1. Google DeepMind Introduces Gemma 3

A multimodal model designed for consumer hardware with advanced vision processing and extended context capabilities.

Features:

• Custom SigLIP vision encoder
• Context support up to 128K tokens (32K for 1B model)
• Multilingual support (140+ languages)
• Models from 1B to 27B parameters
• Knowledge distillation innovations
• Optimized for phones, laptops, workstations, and cloud

2. Tavus Introduces Emotionally Intelligent CVI

An updated Conversational Video Interface that uses emotional intelligence for natural, human-like interactions.

Features:

• Phoenix-3 for full-face animation and emotion control
• Raven-0 for real-time visual cue interpretation
• Sparrow-0 for smoother conversational timing
• Integrated digital twins and AI-powered interviews

3. China Introduces Autonomous Agent Manus AI

An autonomous AI agent that performs complex tasks from start to finish using a multi-agent approach.

Features:

• Autonomous task decomposition and execution
• Versatile use cases
• Integration with existing LLMs (Claude 3.5 Sonnet, Qwen)
• Complete workflow automation

4. Hedra Unveils Character-3 and Studio

An omnimodal AI model that processes image, text, and audio simultaneously, alongside a unified video creation platform.

Features:

• Simultaneous image, text, and audio processing
• Dynamic video generation with natural expressions
• Synchronized lip movements with speech
• Intuitive integrated workflow with real-time previews and API

5. OpenAI Updates ChatGPT for macOS

An update to the ChatGPT macOS app that enables direct code editing in popular IDEs.

Features:

• In-context code editing in Xcode, VS Code, and JetBrains
• Auto-Apply Mode for automatic code edits
• Streamlined workflow without copy-paste
• Real-time code modifications

6. Sakana AI Introduces AI Scientist-v2

An AI system that independently generated a peer-reviewed scientific paper accepted at an ICLR workshop.

Features:

• Autonomous research and paper generation
• End-to-end scientific writing
• Successful peer-review process
• Ethical oversight and transparency
• Competitive review scoring

Other News

• AI21 Labs introduced Maestro to enhance enterprise AI application reliability.
• Meta shared insights on AI business tools and agents development strategy.
• Mistral AI released new OCR capabilities for document processing.
• Google 's Chirp 3 added eight new voices for 31 languages, expanding text-to-speech capabilities.
• Google announced Gemini will replace Google Assistant on mobile devices by year’s end.
• OpenAI redesigned Chat Playground as Prompts Playground with enhanced testing and iteration tools. They also released Agents SDK for production-ready AI applications with integrated orchestration.
• Google updated NotebookLM with Gemini 2.0 Thinking and improved citation features.
• Anthropic upgraded Console for streamlined, Claude-powered application development.
• Alibaba Cloud 's Qwen Team open-sourced QwQ-32B, a 32B parameter reasoning model.

Curated Gems

Simon Willison shared how LLMs can serve as rapid, overconfident coding assistants, speeding up everything from prototyping to full deployments. He breaks down practical tips to help you work faster and smarter without losing that human touch. You'll also get a hands-on case study on tweaking GitHub workflows to reduce development time and cost.

👉🏼 We also just published a new set of docs in our Prompt Engineering Guide for 5 chain-of-thought-inspired prompting techniques you've probably missed: Chain-of-Code, Chain-of-Density, Chain-of-Dictionary, Chain-of-Draft, Chain-of-Knowledge.

Our AI Security Masterclass That Features 9 Top Experts

Join our 6-week Masterclass on AI Security, where you'll learn from leading experts in Generative AI, Cybersecurity, and AI Red Teaming.

We gathered nine AI security specialists who will share their cutting-edge insights and hands-on expertise with you.

• Sander Schulhoff : CEO of Learn Prompting, creator of HackAPrompt, and leader of AI security workshops at Microsoft, OpenAI, Deloitte, Dropbox, and Stanford.
• Jason Haddix : Former CISO at Ubisoft, Head of Security at Bugcrowd, and a top-ranked bug bounty hacker, with extensive experience in penetration testing and AI security.
• Richard Lundeen : Principal Software Engineering Lead at Microsoft’s AI Red Team, developing PyRit, a foundational AI security framework.
• Sandy Dunn : Cybersecurity leader with over 20 years of experience, project lead for the OWASP Top 10 Risks for LLM Applications, and an adjunct professor in cybersecurity.
• Joseph Thacker : Principal AI Engineer at AppOmni, top AI security researcher, and winner of Google Bard's LLM bug bounty competition.
• Donato Capitella : Offensive security expert and AI researcher with over 300,000 YouTube learners, teaching how to build and break AI systems.
• Akshat Parikh : Elite bug bounty hacker, ranked in the top 21 in JP Morgan’s Bug Bounty Hall of Fame, and AI security researcher backed by OpenAI, Microsoft, and DeepMind researchers.
• Pliny the Prompter: Well-known AI jailbreaker, specializing in bypassing major AI model defenses.
• Johann Rehberger : Former Microsoft Azure Red Team leader, known for pioneering techniques like ASCII Smuggling and AI-powered C2 attacks.

Final spots are available. Sign up today!

Enroll Now »

Thanks for reading! Check our blog for more content about prompting and practical Generative AI!