All Segments
Vibe Coding Is The Future
16 segments available
Andrej Karpathy recently coined the term “vibe coding” to describe how LLMs are getting so good that devs can simply “give in to the vibes, embrace exponentials, and forget that the code even exists.” We dive into this new way of programming and what it means for builders in the age of AI. Apply to Y Combinator: https://ycombinator.com/apply Chapters (Powered by https://bit.ly/chapterme-yc) - 0:00 Intro 0:42 What is vibe coding? 1:00 What founders in the current YC batch are saying 4:35 Debugging and building systems 6:59 The models people are using now 10:01 What percentage of code is being written by LLM’s? 11:58 What changed and what stayed the same? 18:08 How Triplebyte did candidate assessments and how would that change in this era 21:37 Key skills that will remain relevant 23:01 How do you develop taste without classical training? 30:59 Outro
Segments Timeline
Embracing Vibe Coding
In this segment, the hosts introduce the concept of 'vibe coding' as coined by Andrej Karpathy. They discuss how this new approach to coding emphasizes intuition and rapid iteration over traditional coding practices. Founders in the current Y Combinator batch share their insights on how this shift is changing the role of software engineers, highlighting the importance of human taste in a world where tools can enhance productivity significantly.
"was like somebody dropped some like giant beanock seeds at night we woke up in the morning going on I mean I think our sense right now is this isn't a fat this isn't going away this is actually the do..."
Founders' Perspectives on Vibe Coding
The hosts delve into the responses from Y Combinator founders regarding vibe coding. They share notable quotes that illustrate the evolving role of software engineers, with some founders expressing a shift from traditional coding to a focus on product engineering. The segment highlights how tools are enabling faster coding and less attachment to code, emphasizing the importance of human creativity and decision-making in the development process.
"surveyed the founders in the current YC batch um to get their take on Vibe coding and we know we essentially ask him a bunch of questions we asked them what tools are you using um what work how has yo..."
The Shift in Coding Practices
This segment discusses the changing landscape of coding practices as influenced by vibe coding. The hosts explore how the ease of rewriting code with LLMs alters traditional debugging methods. They compare the new coding style to creative processes in art and design, where iteration and experimentation take precedence over meticulous step-by-step development.
"that's what we call a back end engineer yeah sure and that's only a theme that came up in these survey responses right this idea of sort of the llms are maybe going to push people to choose do the act..."
Current Tools and Models in Use
The conversation shifts to the tools and models currently being utilized by developers in the vibe coding era. The hosts discuss the rise of Cursor and Wind Surf as leading tools, highlighting their capabilities and differences. They also touch on the use of reasoning models and the importance of adapting to new technologies in the fast-evolving coding environment.
"upon it yet but we haven't seen any of the coding tools right now work well with reasoning I think we have well 03 is infinitely better at debugging than 3.5 onet so like it definitely feels like we'r..."
LLMs and Code Generation
In this segment, the hosts address the significant role that large language models (LLMs) play in code generation. They discuss the percentage of code being written by LLMs and the implications for software engineering. The conversation emphasizes the transformative impact of AI on coding practices and the future of software development.
"is the estimated code that's being written by llms in the current Badger this is pretty crazy so we we explicitly asked this question what percent of your codebase do you estimate is AI generated the ..."
Evolving Hiring Practices in Tech
We explore how hiring practices in tech are evolving to prioritize productivity over classical training. Companies are shifting their focus to candidates who can demonstrate their coding abilities in practical scenarios, moving away from traditional whiteboard interviews.
"the past like I remember they were like coding boot camps like back in the day they would try to like retrain physics people into programmers and like it didn't work that well because it just takes to..."
The Zero to One Challenge
This segment discusses the critical phase of transitioning from zero to one in product development. It highlights the importance of speed in early-stage startups and the challenges that arise as companies scale, necessitating a different skill set for long-term success.
"don't know like active record as a way to like interact with your database was seen as a great abstraction but like there was still this same flavor of argument right like oh know like if you don't re..."
From Quick Solutions to System Architecture
We conclude with a discussion on the need for robust systems engineering as startups grow. While vibe coding allows for rapid feature deployment, scaling requires a deeper understanding of system architecture, illustrating the duality of skills needed in the evolving tech landscape.
"relatively surprising to the four of us here probably pretty shocking out there even it's just like this thing that popped up in our backyard only in the last 6 to nine months my guess would be engine..."
Triplebyte: Revolutionizing Engineer Assessments
The conversation shifts to Triplebyte, a company focused on automating technical assessments for engineers. The founders discuss their approach to evaluating software engineers and the evolution of their assessment methods. They reflect on the importance of tailoring evaluations to specific job requirements, emphasizing the need for a deeper understanding of candidates' skills in the context of modern coding tools and AI.
"to that I think there's very good historical example like Facebook as well I mean they got yeah they got away with PHP which personally is a terrible language yeah maybe I get flame but I think it's a..."
Adapting Assessments for AI-Driven Development
This segment explores how the rise of AI tools impacts the way engineers are assessed. The speakers discuss the necessity of updating technical screening processes to account for the capabilities of AI, suggesting that traditional questions may no longer suffice. They emphasize the importance of evaluating candidates' ability to leverage AI tools effectively while still demonstrating core engineering skills.
"thousands of them right um and then we scaled up and we had like a team of about like 100 Engineers contracted just that that we would pay per interview completed and so you're exactly the right perso..."
The Importance of Taste in Vibe Coding
The discussion highlights the critical role of 'taste' in coding, especially in the context of vibe coding. The speakers argue that even with AI assistance, engineers must possess the ability to discern good code from bad. They stress that developing this taste requires practice and a foundational understanding of coding principles, which remains essential for producing high-quality software.
"much higher you probably have to ask different questions cuz I'll bet if you go back to the original triple bite assessment I bet a lot of those questions you could literally just copy and paste the q..."
Deliberate Practice: The Path to Mastery
In this segment, the speakers delve into the concept of deliberate practice as a means to achieve mastery in software engineering. They reference the 10,000-hour rule and discuss how modern tools can facilitate rapid learning. However, they caution that true expertise requires deep engagement and understanding of systems, drawing parallels to the artistic journey of Picasso in mastering his craft before innovating.
"that's interesting just coder it's like more like code review as the interview versus like actually like producing code yeah I I mean you could have a some form of system design you want to know how g..."
The Importance of Classical Training
In this segment, Karpathy draws parallels between classical training in art and the need for deep technical knowledge in software engineering. He uses Picasso as an example, explaining that true mastery comes from understanding the fundamentals, which allows for innovation and creativity. This discussion underscores the value of being classically trained in a world increasingly dominated by AI tools.
"being classically trained I mean a good example is maybe we go back to history is like Picasso one of the greatest painters it was amazing at drawing lifelike pictures which is not what he's famous fo..."
Navigating Technical Challenges
Karpathy reflects on the challenges faced by technical founders, particularly in scaling their products. He compares Facebook and Twitter's approaches to growth and technical hurdles, illustrating how different usage patterns create unique challenges. This segment highlights the necessity for technical founders to be deeply knowledgeable to navigate these complexities effectively.
"kind of goes back to to link up what we were saying earlier it goes back to hiring I mean I I keep thinking about the Twitter analogy that you brought up CU I think it's a really interesting one like ..."
The Reality of Hiring in Tech
In this candid discussion, Karpathy shares his experiences with hiring and the importance of being able to discern the truth from potential misinformation in the workplace. He emphasizes that technical founders must be equipped to challenge their teams and ensure accountability, especially in a landscape where AI tools are becoming prevalent.
"like 10 times as much usage the way the fan out of the feed works is I think like fundamentally a very difficult computer science problem okay that's fair though I also think that they were like reall..."
Vibe Coding: The Future of Programming
Karpathy concludes with a powerful assertion that vibe coding is not just a trend but the future of programming. He discusses the exponential acceleration of coding capabilities due to AI tools and stresses that those who do not adapt may be left behind. This segment encapsulates the transformative impact of AI on software development and the necessity for engineers to embrace this change.
"technical founder to be classically trained and be a really deep systems thinker well I mean you just I mean a Toby or a Max levchin is not going to get bullshitted by people from stripe is the same I..."