RIP Vibe Coding. Feb 2025-Oct 2025.

Key takeaways

Vibe coding is being reassessed as developers recognize the potential issues with applications created without thorough technical understanding.
AI coding is rapid becoming a defining story for 2025, changing the relationship between model creators and product developers.
The emergence of Agent Labs signifies a shift in focus towards practical applications of AI, challenging the traditional Model Labs approach.
The AI Engineer Code Summit will serve as a platform for discussing the future of software development practices in the context of AI.
Sean suggests that Code AGI may achieve significant value much sooner than full AGI, highlighting the practicality of AI tools in real-world coding.

Summary

The End of Vibe Coding?

In the podcast, host Amar discusses the concept of 'vibe coding' and how it is being viewed as an outdated approach in the current landscape of AI development. With the introduction of tools and platforms that allow non-technical users to create applications—prompting excitement but also frustration among professional developers—there's a growing concern about the quality and stability of applications produced through vibe coding. Sean 'Swix' Wang emphasizes the need to acknowledge the disconnect between novice creators and experienced developers, suggesting that a more structured approach is necessary to ensure software reliability.

AI Coding as a Defining Story

Amar and Sean delve into how AI coding has emerged as a central theme in 2025, significantly shaping conversations in the tech world. They highlight how tools like Google Cloud Code and new startups focused on AI agents are shifting the dynamics between developers (who create models) and product builders (who utilize those models to build applications). This year marks a turning point where coding practices are evolving to integrate AI seamlessly, resulting in ongoing debates around efficiency, standards, and the evolving role of developers.

The Rise of Agent Labs vs. Model Labs

The discussion transitions towards the concepts of 'Agent Labs' versus 'Model Labs.' Amar and Sean outline how Agent Labs, which focus on practical applications of AI, are gaining prominence over traditional Model Labs, which primarily focus on developing the AI models themselves. They speculate on the implications this shift has for enterprises and the software development lifecycle, emphasizing that organizations must now navigate a complex landscape where product functionality and AI capabilities are interwoven.

Upcoming AI Engineer Code Summit

Sean previews the AI Engineer Code Summit happening soon in New York, where he will be featuring discussions on key topics such as memory, context engineering, and organizational transition related to AI adoption. The summit aims to address how teams can adapt to leverage AI technologies effectively, featuring speakers from various enterprises to discuss their journey and insights regarding AI's integration into existing business processes.

The Future of Code AGI

Lastly, Sean shares his thoughts on 'Code AGI,' a term he coined to describe the potential for achieving substantial value from AI-powered coding solutions. He theorizes that this form of specialized AGI could deliver 80% of the benefits of full AGI long before more generalized AGI capabilities are realized. This perspective emphasizes the growing impact of coding tools that leverage AI, outlining how the industry can focus efforts on creating real, verifiable results rather than purely speculative technologies.

Show notes

With NLW currently on the road, he's joined in this conversation by Sean “Swyx” Wang — developer, writer, Latent Space host and newly joined member of Cognition. They explore how AI coding became 2025’s defining story, why “vibe coding” is ending (sort of), what comes next for developers, and how “Agent Labs” are reshaping the balance between model makers and product builders. Swyx also previews the upcoming AI Engineer Code Summit in New York and shares why “code AGI” could deliver 80% of AGI’s value long before full AGI arrives.

Brought to you by:

AssemblyAI - The best way to build Voice AI apps - ⁠⁠⁠⁠⁠⁠⁠⁠⁠https://www.assemblyai.com/brief⁠⁠⁠⁠⁠⁠⁠⁠⁠

Robots & Pencils - Cloud-native AI solutions that power results ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://robotsandpencils.com/⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

The AI Daily Brief helps you understand the most important news and discussions in AI. Subscribe to the podcast version of The AI Daily Brief wherever you listen: https://pod.link/1680633614

Interested in sponsoring the show? sponsors@aidailybrief.ai