Lovable podcast mentions

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

Right. Uh do you see that as a standard that we should invest in? is like a it's like a thing like'cause it's supported in VS Code. I don't think it's just that popular outside of VS Code. Yeah. Uh it's used internally at GitHub too for like d development at GitHub. Oh yeah. Which is cool. Um yeah, I think they were so far ahead almost. Like it was but now they're Sand the s like sandboxes there's so many these days, right? So I think Cloudflare just launched theirs. Yeah, there's digital. Tona, they're here, Russell, um, mo modal, yeah, uh which I think lovable. I don't know what do you what What do you guys just do? Uh just some Kubernetes pods. Okay, you guys roll it yourself. I think that's Maybe the runtime. should be even internally in Microsoft. I've got a couple of different competing things. So we'll we'll figure it out in the next Isn't a dev container you've already got VS code loaded, you've got a file system, you've got sandbox, you've got the security protocol. Yeah. Yeah. And like ready to be packaged. So there's lots of goodness there. But also codex, also presumably the other guys, is repo setup. Effectively what dev containers and a Docker file does for you is like run this

Quote

Important that you start with loving yourself and he says, I love myself, but not in a cherishing or egoistic way, but feeling Feeling the love towards oneself gives you the possibility to share love and feel love towards everyone else. And I think this is such a a deep truth because Dalai Lama was so shocked when he learned that people in the West they don't just love themselves. themselves that often they're full of doubts and having all this concept I should be different, that I can be lovable and And um he really was shocked to to to learn that because this is not a part of the Tibetan culture. difficult question and I think really the Dalai Lama reminds us of of all these aspects. I mean that in the end we are all equal. In the end we are yeah. human beings and we need community, we need mother nature. I mean, we can't survive without having this planet We're so often taken away from these really basic ideas and from this truth with thinking that we need a lot of materialism and that we need need a lot of success for getting these things. Why? I'm not so sure. Maybe because there's a huge pressure in society, maybe because we

Quote

You know, I'm more of the AI assisted coder. Well not the A I'm using AI coding. So these days I'm I'm doing very little coding. by hand, uh, but I'm doing all of the planning, all of the reviewing, all of the uh um everything else. Um so I wouldn't necessarily describe as vibe coding because i hey i just asked the ai to do something i'm not sure how it works but it sort of works uh but um And it might be faster if I would have just go to Lovable or V0 and just say, you know what, just build me a page. Uh but I like the fact that I know what's going on. under the hood, that's one. And it's still a heck of a lot faster than any time in history when I used to to uh code by hand. So that's really the the thing that I need to remember. The fact that I can do it slightly uh faster if I give it full autonomy um I may end up paying it uh uh paying for it in reliability. Right. And of course uh you will still have the control and if some things really really mess mess up or something's uh really taken out of context, I think it's easier for you to handle it rather than completely giving over the autonomy. Yeah. model of the software that we we we used to develop where if a bug happened, we at least had a rough idea of where it's coming from. Not because we anticipated

Quote

The DOD's warning and use the model anyway, despite the glaring vulnerabilities. Exactly. How can we possibly trust these companies to build Build aligned, safe artificial superintelligence if they can't even secure a basic URL. It really is everywhere. Security does not generate venture capital. Shipping new features does. Look at Vercel this week. They had to disclose a breach impacting a subset of their enterprise customers. The attack vector. A hacked AI tool that was connected to Google accounts. Or look at the startup lovable. Oh the lovable story. is insane. Users suddenly noticed that all of their private project chats, including proprietary code base discussions, were completely visible to the public internet online. Lovable. Just out there for anyone to read. Yeah. And how did Lovable's leadership respond? They flat out denied it was a data breach and downplayed the entire incident every day. Aaron Powell A documentation failure that just happened to expose corporate secrets to the open web. Right. Sure. It is a master class in dodging liability. Perhaps the most chilling security story of the week isn't about human hackers breaching the models. It's about the deceptive nature of the models themselves. Anthropic recently ran an internal Safety experiment called Project Deal. This is the study that should absolutely terrify every executive currently trying to replace…

Quote

It's not going to work at larger scale. I see no signs of stopping and the labs are investing everything they have. in there so you know I'm pretty confident. everyone welcome to another episode of the Twimble AI Podcast. I am your host, Sam Charrington. Today I'm joined by Alex Pizan. Alex is an AI lead at Lovable. Before we get going, be sure to take a moment to hit that subscribe button wherever you're listening to today's show. So Alex, welcome to the podcast. Yeah, thank you so much for having me. Super excited to jump into our chat. We're going to be talking about all things vibe coding. To get us started, I'd love to have you share a little bit about your background. Yeah. Um so I've been at Lovable since July last year. I was one of the first engineers. Uh there was a little bit bit before w things took off and you know it became uh what What is today? Um it's been super fun building this. I believed in knowing how to code. I believe a lot in this. And um I joined Lovable because I actually worked on uh on an agent that topped Sweebench for a day.

Quote

this software agent SDK. And then the front end and our GitHub integration and our Slack integration, our CLI all become consumers of this SDK. So those are like more the like last mile developer interfaces. But the SDK now contains basically everything you would need to build a gentic developer experience. And we've seen one One large public company that has built like an internal vibe coding platform for their customers to let their customers take advantage of their technology. So they're forward-deployed engineers now. use this on a daily basis to help their customers write code that interfaces with their systems. That was super super cool to see there's a small, like lovable competitor that's coming up now. They just got their seed round. They're building on top of the Open Hands SDK in order to power their bycoding platform. We're seeing, I've built my own developer work workstation using the open hands SDK, just as this is how I want to work. It really gives you all the nuts and bolts, all the Lego bricks you would need to build, whatever kind of developer experience you want. Okay, let's flip the script a little bit. Tell me about a mistake you made and how you and your team responded to it. Yeah, I would say playing off that same theme, we went way too long just building up tech debt in this monorepo, right? I think one of the tricky things about having a popular open…

Quote

attention and without human effort, you can't make good things. And so the challenge right now is actually to make Norcraft Appealing to invest time in and learn amidst all of this stuff that's a little bit more than a little bit That is based around shortcuts and just say a prompt bro. And it's interesting because we have a lot of internal discussions about about this and it's like our biggest competitors really are the AI platforms like Lovable. and bolt because people are building stuff with that and In a prompt, you know, maybe tweaking it, but like when you wanna build the same thing in Norcraft. Yes, you can start with the prompt, but you we want you to build something. great. We want you to craft something extraordinary. Because you can and you are capable of it. We don't want you just to like accept good enough. And I think that's underpinning the culture of what we build. and also what we want our customers to build and our users to build. And but it that's tough because no one wants to do that. There are very few people that want to do that right now. now because of all of the noise and the hype. Um and that's the biggest challenge. Now I can give you as much education as you want about the web, but it's up to you as a human, as a person.

Quote

Today on the show, Anthropic has taught Claude how to dream, so overnight it can improve itself. Red Access, a security research firm, just published a report that Thousands of apps built on lovable REPL and base forty four are leaking medical and corporate data right now, and Google has quietly killed Project Mariner just two weeks before. for Google IO. Anthropic is on an absolute tear with cloud compute deals, doing one with Google Cloud and also with SpaceX for 300 megawatts with a positive possible future deal where they'll be paying SpaceX to put orbital data centers into space for let's get into some of the Google stories first with Google IO just around the corner. They are making a bunch of changes and it feels like they ship things and aren't really making huge announcements but they have some big some big impact so Google Mariner which is the basically agentic browser Um it was kind of like a Claude Coworker, right? It was supposed to take control of your browser and click and fill out forms and book travel for you, blah, blah, blah. Uh kind of everything that Claude Cowork is doing. Google has shut it down. There wasn't like a big announcement about it, but all of the tech that was in Project Mariner is getting folded into the Gemini agent and kind of the whole agent.

Quote

Today on the show, Anthropic has taught Claude how to dream, so overnight it can improve itself. Red Access, a security research firm, just published a report that Thousands of apps built on lovable REPL and base forty four are leaking medical and corporate data right now, and Google has quietly killed Project Mariner just two weeks before. for Google IO. Anthropic is on an absolute tear with cloud compute deals, doing one with Google Cloud and also with SpaceX for 300 megawatts with a positive possible future deal where they'll be paying SpaceX to put orbital data centers into space for let's get into some of the Google stories first with Google IO just around the corner. They are making a bunch of changes and it feels like they ship things and aren't really making huge announcements but they have some big some big impact so Google Mariner which is the basically agentic browser Um it was kind of like a Claude Coworker, right? It was supposed to take control of your browser and click and fill out forms and book travel for you, blah, blah, blah. Uh kind of everything that Claude Cowork is doing. Google has shut it down. There wasn't like a big announcement about it, but all of the tech that was in Project Mariner is getting folded into the Gemini agent and kind of the whole agent.

Quote

great convergence. And it plums through some similar themes as my episode, Every AI Product is Becoming Every Other AI Product, but puts it in the context of the harness. Nicholas writes, over the last year a strange thing has happened in tech. Very different companies have started moving towards the same product shape, and it feels like everyone is building the same thing. Linear announced Google, Microsoft, Meta, Lovable, Retool, and many others. What changed, he writes, is not just that models got better, although that's a major part of it working. He argues that the important shift is the invention of what he calls the general harness. The simple harness architecture diagram that he describes, a user input hits context engineering, which moves to the model, which calls in tools, Tools, which access context engineering in a loop, until the task result comes out on the other side. Nicholas writes: Claude code was a massive breakthrough, although initially invented for coding use cases, it turns out that a smart looping agent generalizes incredibly well towards any computer-based task if you give it the right tools. So this new technique emerges and turns out to be a general Problem solving machine. It also scales on a very unique dimension. It can keep running for a long time. It takes the shape of a model harness, a goal, and a set of tools. It runs in a loop calling tools.…

Quote

CS. Fin doesn't just answer questions, it takes actions. It automates the most complex customer queries like refunds, transaction disputes, technical troubleshooting. with speed and reliability. I wish my team was speedy and reliable. Beats every competitor in every head-to-head bake-off. Completely configurable and code optional. setup. My word. I mean the benefits just go on and on. It's easy and efficient implementation. It works on any help desk with no tedious migration needs. It's trusted. By over 6,000 customer service leaders, including top AI companies like Anthropic, Lovable, Synthesia, Clay, Vanta. So if you're ready to transform your customer service team. Scale your support and give team members time to focus on the really high level strategic work. Learn more about Finn at Finn.ai forward slash two zero VC. If it scales your support without losing speed, ReFord shows you how to translate that scale into durable product-led growth. Everyone shipping faster than ever. Cursor. Claw code, codecs. AI is making code and writing code faster than ever. But here's the problem speed means nothing if nobody uses what you ship. That's where Reforge comes in. Reforge is building the product discovery engine that sits upstream of your coding agents. Not another prototyping tool research repo or AI interviewer, but a product that will ingest your customer data, generate variati…