Cursor podcast mentions

Quote

Custom packages stay isolated, model outputs flow seamlessly between workflows. Companies like Whoop and One Password also trust Prefect for their critical workflows, but Prefects Didn't stop there. They just launched FastMCP, production ready infrastructure for the first time. AI tools. You get prefects orchestration plus instant OAuth serverless scaling. Claude, cursor, or any MCP client, no more building auth flows or managing servers. Prefect orchestrates your ML pipeline. Fast MCP handles your AI tool infrastructure. Structure. See what Prefect and FastMCP can do for your AI workflows at AI Engine. Podcast dot com slash prefect today. Bruin is an open source framework that streamlines integration from the command line, allowing you to focus on what matters most. Write Python code for your business logic and let's see. and handle the heavy lifting of data movement, lineage tracking, data quality monitoring, and governance enforced. Enforcement. With native support for ML and AI workloads, Bruin empowers data teams to for hundreds of platforms, including popular machine learning frameworks like TensorFlow and PyTorch.

Quote

people who understand the code anymore, it's gonna be zero. Right? And in that world Well, how do we maintain it? Like what happens? How do we support it? um at any sufficient scale. Um and I think a lot of those realities are starting to be realized now. Um you started this company in in 22, um, I guess late 21. Um you know pre-Chat GPT kind of with this understanding that that what we're seeing now with vibe coding with energetic development um cursor windsurf the likes, um, you know, basically kind of anticipating. the future that we get to live in today. With that in mind, like Uh especially you said you've been working on this for three or four years. Like what it how's it been to watch the uh advent of you know ai assisted coding and uh agentic coding, vibe coding, all of this like it it, you know. It both you know, it it was it's both something that you know we You've been able to anticipate for a really talk long time, but also something that like exploded all you know, seemingly overnight and I'm curious, um, you know, when You think about it, what stands out for you as kind of the most interesting aspects of

Quote

You know, twenty, thirty plus years. And so it's important to be going from, you know, one hundred and one dot three to I think for us, so what's been actually pretty interesting is we See, there's kind of two different users for us that are coming in, and it's very distinct. It's like people that are developers already and then there's people that have never really written software. And I'm Or if they have it's been very, very minimal. And and so in the first camp, what these developers are doing, like to go from zero to one. and they're coming to bull and then they're ejecting the thing to GitHub or just downloading and, you know, opening cursor like whatever to to you know keep iterating on the thing and sometimes they'll bring it back to bolt to like add in a huge piece of functionality or something, right? But for the people that don't know how to code, they're actually just they they live in this thing. And that was one of the weird things when we launched is you know, within uh a day of us being online what One of the most popular YouTube videos and there's been a ton since, which was you know, there's like, Oh Bolt is the cursor killer and And I originally saw the headlines and I was like, thanks for the views. I mean, I don't know this doesn't make sense to me. That's not what we kind of thought. It's how YouTubers talk to each other. kills everything else. Totally, b…

Quote

You're in the world of of rag, let's let's say, so to speak, in in a in a sense. Do you think that there will be some more integrated tools like yourself with Some of the the major LLM processes just for general use this year. Do you think that'll get improved um try like open AI and big players or how do you think that's gonna play out? Look, I think in the last twelve months we've seen kind of the current Cursor moment and the lovable moment. Right. And cursor ha cursor's been unbelievable. And I think that there is like we should all study that as an industry and say like what were the ingredients? that led to the explosiveness of their growth. And so what Cursor did is they What they didn't do is go develop entirely new models from scratch and try and compete head Sure. do was go and develop new vector db architectures, right? They elegantly packaged was a user experience that um Um that took user like our code at Unstructured or you know our engineer she's crypto. Yep. Or or quad coat. Uh package it with turbo puffer. I think there's still use turbo puffer um as an incredibly effective t uh vector database for that use case. hooked it up to the LLMs and were able to unlock a lot of value. So you had

Quote

been 10,000, 20,000 tokens just like in this loop and it's like not really getting anywhere and I was like, I mean, if you can make debugging easier for humans. You can potentially make it easier for bots too, and that's that's interesting. That's the idea. Yeah, I feel I feel like if you guys make that powerful enough there's some uh AI coding companies that'll want to snatch you up. replay could be in the context of AI. I'm like I I need that in my cursor like right now. I need it yesterda We've only begun to explore the possibilities of having a time travel API. I mean I I have so many other ide I mean in fact uh I don't know maybe summer. twenty three ish, I I've started to play with performance analysis, like the proof of concept that could look at a a redux dispatch trace through a whole re Redux render cycle and tell you exactly which selectors ran, how long recording and do a full breakdown of where all the time was being spent in the That process. Uh I I would love to revisit that one too.

Quote

It really was. Carpathy coined the term back in February twenty twenty. twenty five. He defined it as this um relaxed, intuitive style of programming. The core idea is that the developer relies almost entirely on natural language description. to generate code. It's a go-with-the-flow mindset. So instead of assessing over syntax, or memory allocation or you know m memorizing the standard library for Python, you are just You're dictating. Exactly. You are using tools like Cursor Composer, usually paired with a model. like Sonnet, the workflow is basically you tell the AI, make this button blue, hook it up to the database. And throw a confetti animation when I click it. And the AI generates the diffs, the actual code changes. And you just hit accept. Without reading it. Ideally, yeah. In a pure vibe coding state. Yes. You accept the changes without a deep code review. If the app crashes you don't open the debug review. and look at a stack trace, you just tell the AI, hey, that break the login page, fix it. Herpathy described building projects where he forgot the code even exists. I have to admit, that sounds incredible for productivity. It is wildly productive for creation. That's the appeal, right? It offers massive leverage. You can turn a weekend hackathon idea. Oh the app that visualizes

Quote

thing to say. A business is based on a number of people. Their brain power is They're gonna have to get together and track things. Um we've built A series of features recently for uh assigning work to agents, either our rovo agents. or uh agents that come from other agentic platforms, be that um you know, Salesforce or or Google Agent Space, uh or B that from I don't know, Cursor or or uh GitHub Copilot, for example. There are code writing agents and there are lots of business writing agents. Being able to assign a piece of work to an agent is a really powerful feature to have in a work management tool. What that agent does is up to the agent. So if I have a marketing project and I assign something off to um you know uh writer or one of these startups that can do interesting things in certain domains? Awesome. What happens when that work is done? In a business, it's gonna come back. It's gonna add a file. It's gonna send me a link. add a comment, a piece of text. Maybe another agent picks it up, maybe a human being picks it up. And Maybe that needs to be approved or authorized or sent to another department to print it or to send. it out to the world or do something. Um these business workflows and processes are what I think is the most fascinating part of how I is gonna optimize things. I think we're in a world where people go, oh well

Quote

automate more and more. And I I think that you're right. So um Shoshank is referring to uh this project that I made. I think it was probably like like two or three years ago now, um, that I call GPT engineer. So um I built flawed code like probably two or three years before Claude Code actually even existed. Um before, you know, before cursor, uh before Devin, uh before all of this, like I had GPT engineer which actually um worked uh as well. So So uh yeah, but I I gave it away for free and didn't really market it much. So Um I that's why I'm not a billionaire. Because I was I was actually first. I I I built Uh like the pretty much like what they had for uh something like CloudCome. And uh, you know, looking at like the Claude Code uh source code from the leak. GPT Engineer, which I built like three years ago, was actually not that far. far off um from what I had, but they just waited for the models to get better. It's not that different. Yeah. No, it like the the the the logic was was the same. Um but yeah I I think that uh

Quote

Ader, this this um coding tool um where uh you construct like um uh repository map and sort of have some level of abstraction, but they also come again with uh Positive uh and negative trade offs basically. I I love Ada by the way. Um It it feels that in the future the um the aud you know, like the code generation systems will will actually resemble Shinkarville. Maybe Cursor already does this because in Cursor you can merging checkpoints together and um you know obviously you you just say in natural language what you want to do. But um we didn't talk about mutation by the way so so we just spoke about diffs and then There's also an option to do the a full file rewrites. But there's also this notion of crossing. So how how does that work? only use sort of th diff based um um mutations is that here we wanted to have more than a few yeah. Flexibility to entirely rewrite the program, right? To come up with a completely different step. So um again there you can make parts of the code mutable, but Instead of proposing uh let's say a patch to change certain parts of it, we um actually rewrite the entire program. And um this sometimes is helpful, right?

Quote

Pretty big bills of which we which we swallow at the moment. Yeah, I I think over time as Brunola kind of transitions to kind of more directly doing work for you as like rather than just being a kind of companion or a or whatever. Like uh um I think I I think we'll have to look at the pricing plans and how we I think usage-based pricing or like a cursor or or clawed model. But I I think there is uh Um there's something very nice and and transparent about like paying a price. and getting a getting a thing and especially especially while people think of us as like a That's a that's the core of it. People really like the simple seatbacks thing. Yeah, that echoes a lot of my kind of experience and general advice I've given over time. Although you've taken And then the question just becomes can you get all the way to a unicorn valuation before? you really have to get serious about that? And I guess the answer is yes you can. So I can't. The line of up burn rate we we flooded a we have a line that we keep up to date of.

Quote

specific in nature. And so the more specific that the AI officers can get, the use cases. And define and have narrow boundaries for AI projects, I think the fastest that they can actually accomplish a lot of change. What I also find Which is the third pillar, which is it is also a qua question of um adoption because you know AI is a big hit, a roaring hit in consumer. It's a roaring hit in prosumer for companies like you know Cursor Claude, you name it. But where it is kind of um you know not there is in the enterprise right now. And I think I'm gonna make a prediction that in the next twelve to eighteen months we'll see massive. And it is because the what it requires is that and enterprise. Enterprise AI is not a a solution to all your problems, but it is a great solution to a lot of your complex problems. And I think across the enterprise when you go And look at and ask the leaders what are you doing today? They are already doing a lot of automation on the front office. They've done a lot of automation in the middle office. And I think the back office is just there. We saw this with cloud adoption as well. And so there are like ringing parallels on this. And then it slowed down and then it picked up like it never picked up.

Quote

Welcome to the podcast. I'm your host Jaden Schaefer. Today on the show, Anthropic has just announced Opus 4.7, the latest model, and there's a lot of crazy AI, what cursor did for software development. It's basically a simulation to real play for robotics and I think the framing they're using is super smart so I want to get into all of that. Then And this one I think is also really interesting. There is a company called Upscale AI. It's reportedly In talks to raise a two billion dollar valuation round. It's only seven months old. There is No product yet. And I think what that tells us about AI infrastructure investments right now is definitely really important to understand. And then of course we have the fact that Google Cloud M. Avid just announced a multi-year partnership to bring Gemini AI Cloud directly into the tools. that professional media and video editors are using every day. So we're gonna get into what that actually means. Google also dropped an annual ad safety report, which inside of it they showed that they blocked eight point three billion ads f uh last year using their AI powered information enforcement and the way that they did it, I think, is a big shift in how this kind of automation enforcement is working.