Best Podcast Episodes About GitHub
Everything podcasters are saying about GitHub — curated from top podcasts
Updated: Apr 02, 2026 – 51 episodes
Listen to the Playlist
Ridealong has curated the best and most interesting podcasts and clips about GitHub.
Top Podcast Clips About GitHub
“… and tests and all of those things and it looks like the kind of software the previous i've spent several weeks on and i can stick it up on github and everything and yet i don't believe in it and the reason i don't believe in it is that i i got to rush through all of those things I think the quality is probably good, but I haven't spent enough time with it to feel confident in that quality. Most importantly, I haven't used it yet. Like it turns out when I'm using somebody else's software, the thing I care most about is I want them to have used it for months. I want other people to have …”
“… software, I think is going to be valued more. something i've noticed in my own work is sometimes i'll have an idea for a piece of software python library or whatever and i can knock it out in like an hour and get to a point where it's got documentation and tests and all of those things and it looks like the kind of software the previous i've spent several weeks on and i can stick it up on github and everything and yet i don't believe in it and the reason i don't believe in it is that i i got to rush through all of those things I think the quality is probably good, but I haven't spent enough time with it to feel confident in that quality. Most importantly, I haven't used it yet. Like it turns out when I'm using somebody else's software, the thing I care most about is I want them to have used it for months. I want other people to have put that software into practice. So I've got some very cool software that I built that I've never used. Like it was so it was quicker to build it than to actually try and use it. And so the way I've been dealing with that, I've always put alpha on it. Like if you see my software and it says it's an alpha, that probably means I haven't actually used …”
View more
Ridealong summary
Despite AI's promise of increased productivity, many engineers feel more exhausted than ever, working harder to meet rising expectations. This paradox raises concerns about burnout while also sparking creativity, with developers rapidly completing long-standing side projects. As the AI boom continues, the tension between efficiency and quality becomes increasingly apparent.
“… code. Claude code leak. I don't know why I couldn't say that. A bunch of Anthropics code got leaked all over the internet. They shut down a bunch of GitHub repos as they were trying to contain the leak. Lots of people dove into the code. Some people reverse engineered it. It was discovered that Anthropic is trying to build a Tamagotchi-style pet and an always-on agent into Claude, which, okay. Side note, I did use Dispatch. I'm using Dispatch more, and it's pretty cool. Also, have you ever used Dispatch with Claude? Isn that where you can send a messages from your phone or whatever You can send a …”
“… waiting for that update. Every time an update comes, I'm like, CarPlay? But no. Radio silence. No. I don't think it's going to happen. We'll see if it happens. Also, this was huge news. So there was a massive Claude call. Claude call. Wow. Claude code. Claude code leak. I don't know why I couldn't say that. A bunch of Anthropics code got leaked all over the internet. They shut down a bunch of GitHub repos as they were trying to contain the leak. Lots of people dove into the code. Some people reverse engineered it. It was discovered that Anthropic is trying to build a Tamagotchi-style pet and an always-on agent into Claude, which, okay. Side note, I did use Dispatch. I'm using Dispatch more, and it's pretty cool. Also, have you ever used Dispatch with Claude? Isn that where you can send a messages from your phone or whatever You can send a message from your phone and then have your computer do stuff The problem is it doesn talk back to you so i never know like what it doing it just it say like red like it give you like a red receipt but then like i don know what it doing so it like you get home and it's just changed all your smart locks and you're how did you change this lock you're …”
View more
Ridealong summary
You can now chat with ChatGPT directly through CarPlay, making your drive more interactive than ever. Meanwhile, a major code leak from Anthropic reveals their ambitious plans for Claude, including a Tamagotchi-style pet feature. This leak poses significant competitive risks for the company as they scramble to contain the fallout.
“… to as dreaming. There's also a piece that tells Cloud Code to hide the fact that it's an AI in certain situations, like when it's pushing code to GitHub. Someone found a reference to a Tamagotchi-style virtual pet called Buddy that people can interact with. If Claude is Oz, this link gave everyone a pretty good look behind the curtain. Neil, this is a double whammy for Anthropic. There's the hit to its reputation as the quote-unquote safe AI company. And then there's the hit to its actual business since competitors now know some of its inner workings. It is a claudatastrophe. For developers, …”
“… to the Wall Street Journal, the leak was a goldmine for competitors who want to know what Anthropic's secret sauce is. One of the leaked features involves the model revisiting past tasks to remember what it's learned, a process Anthropic refers to as dreaming. There's also a piece that tells Cloud Code to hide the fact that it's an AI in certain situations, like when it's pushing code to GitHub. Someone found a reference to a Tamagotchi-style virtual pet called Buddy that people can interact with. If Claude is Oz, this link gave everyone a pretty good look behind the curtain. Neil, this is a double whammy for Anthropic. There's the hit to its reputation as the quote-unquote safe AI company. And then there's the hit to its actual business since competitors now know some of its inner workings. It is a claudatastrophe. For developers, this is like a kid going to Disney World for the first time. You have the world's, maybe the world's foremost AI company who employs the smartest AI nerds on planet Earth, basically just handing you their closely guarded trade secrets. It's like a free world-class engineering education. No surprise that this spread like absolute wildfire in developer …”
View more
Ridealong summary
The leak of Anthropic's Claude code is a major blow to its reputation and business, as it exposes trade secrets and gives competitors a significant advantage.
Anthropic's massive code leak is a catastrophic blow to its reputation and competitive edge, exposing its trade secrets to rivals and developers alike.
“… things that you have to copy wholesale. So in the next show that I do this week, it's going to be a personal context portfolio. And I'm sharing a GitHub repo that has basically templates for 10 files about yourself. And it's sort of it's not meant to it's not something you would copy. It's about yourself. So you have to use it like a template. But I think there's a lot of resources out like that. And so I think it sort of puts a fine point on the idea of wanting to have the skills to build because it actually unlocks using all of these things that are out there in different ways that aren't …”
“… on more heavily towards building at this day and age. One note on that front. I agree entirely. I also think that by virtue of them being sort of marked, you know, just markdown files, you can also treat even skills that you download as templates, not things that you have to copy wholesale. So in the next show that I do this week, it's going to be a personal context portfolio. And I'm sharing a GitHub repo that has basically templates for 10 files about yourself. And it's sort of it's not meant to it's not something you would copy. It's about yourself. So you have to use it like a template. But I think there's a lot of resources out like that. And so I think it sort of puts a fine point on the idea of wanting to have the skills to build because it actually unlocks using all of these things that are out there in different ways that aren't just sort of blindly copying it into your projects and hoping it works. Yeah. And by the way, versus custom GPTs that were black boxes, if you were to use others, now you get the full visibility into how the skill is instructed. So if you don't like some of it, just change it. I just wanted to note that Claude created an amazing, and Tropica rather, …”
View more
Ridealong summary
Creating your own skills can dramatically enhance your understanding and effectiveness in using them. By leveraging templates and structured instructions, you can unlock the full potential of these tools. This approach not only makes you a better builder but also empowers you to customize existing skills to fit your needs.
“… the news and i was like no surely there must be wrong like this is hyperbolic. But no, the entirety, it's all there. You can go and read it. It's on GitHub. And it's funny because they're actually actively trying to take down the repos that forked the code. But some guy rewrote the entire thing in Python this morning because you could just do that”
“… closed way and they're using internally and it creates a lot of these interesting problems to look out for but in terms of the leak today that's the news it was a big leak i can't believe that actually happened like i woke up this morning and i read the news and i was like no surely there must be wrong like this is hyperbolic. But no, the entirety, it's all there. You can go and read it. It's on GitHub. And it's funny because they're actually actively trying to take down the repos that forked the code. But some guy rewrote the entire thing in Python this morning because you could just do that”
View more
Ridealong summary
The leak of Anthropic's Claude code is a catastrophic security failure, revealing their entire roadmap and compromising their competitive edge.
Anthropic's repeated security failures are catastrophic, revealing their entire roadmap and compromising their competitive edge.
The leak of Anthropic's AI code is damaging to its reputation but beneficial for the open source community, providing access to its roadmap and features.
The leak of Anthropic's Claude AI code is a reputational hit but a boon for the open-source community, revealing their roadmap and enabling broader experimentation.
“… divert attention from humans towards the machines. And so the machines are downloading, but the machines are not interacting with the developer on GitHub. And so that already seems to be. So this is data for basically 2025, where I think a lot of the agentic software revolution was happening. And so already in the first year of that, you can see this effect. I'm curious, if you extrapolate out the use of agents selecting these different libraries for inclusion, especially since you very specifically did not constrain that in the prompt up front. You gave it the choice of doing that. If you were …”
“at least the mechanism and the model is that you divert attention from humans towards the machines. And so the machines are downloading, but the machines are not interacting with the developer on GitHub. And so that already seems to be. So this is data for basically 2025, where I think a lot of the agentic software revolution was happening. And so already in the first year of that, you can see this effect. I'm curious, if you extrapolate out the use of agents selecting these different libraries for inclusion, especially since you very specifically did not constrain that in the prompt up front. You gave it the choice of doing that. If you were to kind of take that out to the extreme case, is there, given the fact that a lot of the, not only the libraries, but a lot of the tooling, you know, the very notion of version control and such are really human constructs that, you know, we humans historically are trying to deal with complexity as we're writing code. And we have created all of …”
View more
Ridealong summary
AI is transforming software development into a collaborative experience, acting like a highly capable coworker rather than just a tool. As developers learn to structure their code better, AI can enhance productivity by understanding and executing tasks based on well-defined requirements. This shift emphasizes the importance of good coding practices in maximizing the benefits of AI assistance.
“… released this thing called auto research. It's a piece of open source software. It's only 600 lines of Python code. It's already had 57,000 stars on GitHub. And what auto research does is it enables AI systems and you running an AI system to automatically conduct research. I said, look, this could probably work outside of the machine learning domain. Could we find some other way of defining the objective, right? Why does it have to be the loss function in an ML product? Couldn't we define a business objective? So my new setup is this new version of auto-research. And what that allows me to do is …”
“Today, I wanted to talk about a little tool that I came across about a month ago that has really changed the way that I do some of my work. And that was a tool released by Andre Carpathie. Now, what did Carpathie release? He released this thing called auto research. It's a piece of open source software. It's only 600 lines of Python code. It's already had 57,000 stars on GitHub. And what auto research does is it enables AI systems and you running an AI system to automatically conduct research. I said, look, this could probably work outside of the machine learning domain. Could we find some other way of defining the objective, right? Why does it have to be the loss function in an ML product? Couldn't we define a business objective? So my new setup is this new version of auto-research. And what that allows me to do is run this iterative loop, this scientific loop, hypothesis-driven testing, automatically on all sorts of commercial, intellectual, academic, theoretical problems that are relevant for us. This is a reduction in the cost of the scientific method. You know, I'm applying this scientific method now to questions that benefit from it where it would have …”
View more
Ridealong summary
Andrej Karpathy's autoresearch tool transforms scientific experimentation, making it accessible and affordable for everyone. By applying an iterative scientific loop to various problems, this open-source software allows users to define objectives beyond traditional machine learning, effectively democratizing the scientific method. This innovation could break humanity out of resource constraints, enabling us to produce knowledge more efficiently than ever before.
“… it's stable in terms of its value. So before we get to the really exciting stuff you're doing now, OpenClaw went from zero to I think over 145,000 GitHub stars in two weeks, 1.5 million agents transacting on Moldbook. Some people are calling it the early singularity I not one of those Others are calling it a dumpster fire I closer to that Where do you land Maybe both in a way So I think the positives I would say is that very quickly many more people have suddenly experienced this idea of a layer of abstraction above, say, cloud code or chat or co-work, even, you know, these new sort of what they …”
“… in value, so that if I'm sending you money, how much money you receive might be quite different than the money that I sent, and neither one of us can know ahead of time. And so the idea of a stable coin is that I send you $10 and you get $10, and it's stable in terms of its value. So before we get to the really exciting stuff you're doing now, OpenClaw went from zero to I think over 145,000 GitHub stars in two weeks, 1.5 million agents transacting on Moldbook. Some people are calling it the early singularity I not one of those Others are calling it a dumpster fire I closer to that Where do you land Maybe both in a way So I think the positives I would say is that very quickly many more people have suddenly experienced this idea of a layer of abstraction above, say, cloud code or chat or co-work, even, you know, these new sort of what they had thought of as how you interact with the AI, sort of a layer above that that can use all of those things under the covers. And so the Appetite is there. And, you know, the interest and enthusiasm for those kinds of actors is there. More on the dumpster fire side is that, you know, they're just tremendous security implications. I think that, you …”
View more
Ridealong summary
The future of AI agents as economic actors hinges on building trust, but current developments raise serious security concerns. Sean Neville discusses how the rapid rise of AI transactions has created both excitement and anxiety, highlighting the potential for AI to democratize access to finance while warning of the risks involved. Trust is essential for AI to become accepted financial participants, and we must address the security implications to ensure safety in transactions.
“… side, things have changed. I think everyone's probably seen, you know, every CEO out there is going on Twitter and showing their like green dot on GitHub. But that's real. Like all of our designers are shipping PRs. All of our product managers are shipping PRs. That's not that interesting anymore. I think more interesting is that we have internal tools that are similar to Claude Code, but they're like more plugged into our infrastructure. So we have a tool called BuilderBot. But BuilderBot is just autonomously merging PRs and actually building features to 100%. We've had some fairly complex …”
“I think that then in terms of how we actually build on the development side, things have changed. I think everyone's probably seen, you know, every CEO out there is going on Twitter and showing their like green dot on GitHub. But that's real. Like all of our designers are shipping PRs. All of our product managers are shipping PRs. That's not that interesting anymore. I think more interesting is that we have internal tools that are similar to Claude Code, but they're like more plugged into our infrastructure. So we have a tool called BuilderBot. But BuilderBot is just autonomously merging PRs and actually building features to 100%. We've had some fairly complex features that are built to 100%. More often than not, it's building them to 85% or 90%. And then a human who has a lot of context and understands does the final 10%. So that feels really, really different. The ability to go from idea to this is in the hands of 100,000 or a million customers has been compressed massively since December. Outside of …”
View more
Ridealong summary
Block's internal tool, BuilderBot, is revolutionizing how features are built, achieving up to 90% automation in development. This shift allows the company to respond to customer needs faster than ever, compressing the time from idea to customer delivery significantly. As AI takes over routine tasks, human oversight remains crucial, but the future clearly favors automated systems over traditional workflows.
“… that rip YouTube videos and constantly get blocked. Then it was like, oh, that's not working. It's not consistent. We should probably just run this GitHub repo that was based upon what those websites are because it's open source software. I was like, yeah, that sounds great. Now, I just go to like three of my replicants, Lon's, myself, and another one, and I just say, hey, can you get me this video? It downloads, it puts it back into the Slack room. And then for larger ones, it puts it into a G drive. But I figured that out, not by going and doing the research myself, just by asking the …”
“… me to download videos, rip a video from Instagram or Twitter and get it into my, and then store it somewhere. And we figured out, or it figured out like three or four different ways. One of them was on my Mac mini to go to like these Russian websites that rip YouTube videos and constantly get blocked. Then it was like, oh, that's not working. It's not consistent. We should probably just run this GitHub repo that was based upon what those websites are because it's open source software. I was like, yeah, that sounds great. Now, I just go to like three of my replicants, Lon's, myself, and another one, and I just say, hey, can you get me this video? It downloads, it puts it back into the Slack room. And then for larger ones, it puts it into a G drive. But I figured that out, not by going and doing the research myself, just by asking the replicant, talking to your agents is all you need. Point number two, three, put your agents on a cron schedule, and then you can really see the power of them. Number four, add cross-agent memory when you start scaling. This is something, it's interesting, that you bring this up that we, Oliver, who is the producer of This Week in AI and does the demos …”
View more
Ridealong summary
By simply asking your AI agents for help, you can streamline tasks that would otherwise take hours of research. For instance, when I needed to download videos, I discovered that my agents could autonomously find the best methods, saving me time and effort. This approach not only enhances productivity but also showcases the power of effective agent management.
“… packages. It's also automation. I mean, they were, it sounds like it was a CICD issue. And by the way, this, this happened a couple of weeks ago, a GitHub CICD issue with GitHub actions. And I keep seeing this again and again.”
“… of reach, rendering them impractical. So we knowingly and deliberately create dependencies upon sprawling packages over which we have no oversight or direct control. All we can really do at this point is hope that our luck holds. It's not just the packages. It's also automation. I mean, they were, it sounds like it was a CICD issue. And by the way, this, this happened a couple of weeks ago, a GitHub CICD issue with GitHub actions. And I keep seeing this again and again.”
View more
Ridealong summary
A recent hack in Light LLM nearly unleashed devastating malware across millions of AI systems, but a critical flaw in the attackers' code led to their downfall. This incident underscores how fragile the security of our open-source ecosystem is, as reliance on poorly managed repositories can create dire consequences. Thankfully, quick actions caught the malware before it could cause widespread damage, highlighting the need for better security practices.
“… anywhere, and that is a good argument to be made. Well, let me tell you about Graphite. Code review for the age of AI. Graphite helps teams on GitHub ship higher quality software faster And let me also tell you about Eleven Labs Build intelligent real conversational agents Reimagining human technology interaction with 11 labs We have to start apologizing to the schizophrenic community There was a surveillance drone reportedly flown by infiltrator elements and disguised as a natural bird, such as an eagle, that has been spotted in a round. This goes back to Taylor Lyons because I believe she …”
“… the alarm bells around age verification. It sounds very good. I feel like I'm pro-age verification based on, like, I have kids, and I don't want them seeing adult content. But she was worried about the KYC and needing to be tracked, privacy, tracking anywhere, and that is a good argument to be made. Well, let me tell you about Graphite. Code review for the age of AI. Graphite helps teams on GitHub ship higher quality software faster And let me also tell you about Eleven Labs Build intelligent real conversational agents Reimagining human technology interaction with 11 labs We have to start apologizing to the schizophrenic community There was a surveillance drone reportedly flown by infiltrator elements and disguised as a natural bird, such as an eagle, that has been spotted in a round. This goes back to Taylor Lyons because I believe she worked with the folks behind the viral stunt, Birds Aren't Real, that was sort of a commentary on the conspiratorial nature of the internet. And in that stunt, they make the argument that birds need to be recharged and they're all spying on you and no birds are real. Of course, that is very satirical and funny. But apparently someone made a drone, …”
View more
Ridealong summary
Meta and YouTube may have to overhaul their platforms following a recent trial that holds them liable for users’ screen time addiction. This ruling could force significant changes, including age verification and the removal of features like infinite scroll, impacting their ad revenue models. As the case heads to appeals, experts warn this sets a dangerous precedent for tech companies everywhere.
“… project and want to have a quick idea of how it breaks down Talonman can give you a good overview Yeah it like a much more detailed version of the GitHub little sidebar there that tells you what languages are used in it Yeah pretty cool. Awesome. Well, thanks, Chris, for coming back on the show this week and sharing all these PyCoders goodies with us. Cheers. All right.”
“… it off, it also summarizes the output, grouping things like code, spec, design, and data together, giving you output on all the different parts of your project. So if you want to know a bit more about what you working on or if you diving into a new project and want to have a quick idea of how it breaks down Talonman can give you a good overview Yeah it like a much more detailed version of the GitHub little sidebar there that tells you what languages are used in it Yeah pretty cool. Awesome. Well, thanks, Chris, for coming back on the show this week and sharing all these PyCoders goodies with us. Cheers. All right.”
View more
Ridealong summary
Philippe Mameli introduces a groundbreaking Python project template that streamlines the creation of data projects using modern tools. This template leverages the Copier tool for bootstrapping, along with popular technologies like UV, Ruff, and Marimo, making it easier than ever to manage and visualize your data effectively. If you're looking to enhance your data project workflow, this is a must-see resource.
“… like, oh crap, okay. So I did the work again and I was like, I'm going to submit this. And I was like, can I just like copy and paste the file into GitHub? No, you can't do that. You first make a fork of the project. Then you make your changes in your version of the project, commit them to your version of the project. and then you go back to the original project and you hit the button that says new pull request and you say i want to do my version of this project against their version of this project there's five changes or eight changes or whatever and uh most projects have like a little thing …”
“… you have to pull a handful of things and basically integrate them in this Python file and update some documentation. And I got it working on my machine and then I updated Liquid Control a couple of days later by accident. It stopped working. I was like, oh crap, okay. So I did the work again and I was like, I'm going to submit this. And I was like, can I just like copy and paste the file into GitHub? No, you can't do that. You first make a fork of the project. Then you make your changes in your version of the project, commit them to your version of the project. and then you go back to the original project and you hit the button that says new pull request and you say i want to do my version of this project against their version of this project there's five changes or eight changes or whatever and uh most projects have like a little thing that you fill out that says yeah i tested this and i i did here's what i did blah blah blah blah i did all the things that you want me to do to before you submit a pull request and then i hit the button that said that and like two days later it was in the it was in the it was in the software and you can download it from the repo. You got merged. …”
View more
Ridealong summary
Successfully submitting a pull request can feel overwhelming, but it leads to significant improvements in software. The process involves forking a project, making changes, and submitting them for review, which can yield quick results. After navigating the complexities of Git, one user found their contributions merged into the software in just two days, showcasing the rewarding nature of collaboration in open-source projects.
“… on the release schedule and with the same requirements as Laravel has, and then you can come back later and see if that happens. I literally have a GitHub saved response that says exactly that, basically. You should go build this as a package and see if it gets traction and then come back. Yeah. And that's been super successful, especially, I think, thing people don't get, which is like the other message for contributors that is important to hear is like most of these like open source repos do not have like a Microsoft level triage team where they have, you know, like five people on staff to read …”
“… NeoVim core. And, like, I think that's a way better strategy, too. If you're like, oh, there's this big thing that Laravel needs or something, right? Go and build, like, the external version of that. Iterate, iterate, iterate, iterate, iterate. not on the release schedule and with the same requirements as Laravel has, and then you can come back later and see if that happens. I literally have a GitHub saved response that says exactly that, basically. You should go build this as a package and see if it gets traction and then come back. Yeah. And that's been super successful, especially, I think, thing people don't get, which is like the other message for contributors that is important to hear is like most of these like open source repos do not have like a Microsoft level triage team where they have, you know, like five people on staff to read issues full time, right? Where it's like, oh, we're Microsoft's budget for VS Code is like multiple millions of dollars per year, Right. And so, yeah, that's fine. You can just like, oh, they want to have a built in package manager that does all of this stuff and whatever. Cool. They can put a few engineers on that and spend several million …”
View more
Ridealong summary
The best way to contribute to open source is to build a separate package first, test it, and see if it gains traction before merging it into the main project. Many open source projects lack the resources of big companies, making this iterative approach essential for effective contributions. This strategy not only helps contributors avoid burnout but also ensures that their ideas are well-tested and viable.
“… lot easier to use than opening up a terminal. So this was all great. And the problem is that the original OpenClaw Git repo, which has like 330,000 GitHub stars, I mean, it's an incredibly popular, it might be the most popular Git repo ever. the problem is that it's security swiss cheese you literally can't use it anywhere and if you put it on your own laptop you have to be dangerously insane like this needs to go in its own little house or up in the cloud you put it in gcp and cloud run and you leave it there and you let it do what it does well it's the reason that uh mac minis are sold out yeah …”
“… best was was make Claude code feel like it was alive and working for you on a full basis and they did something really smart Peter Steinberger did something really smart He made it available in whatever chat client you happen to like which made it a lot easier to use than opening up a terminal. So this was all great. And the problem is that the original OpenClaw Git repo, which has like 330,000 GitHub stars, I mean, it's an incredibly popular, it might be the most popular Git repo ever. the problem is that it's security swiss cheese you literally can't use it anywhere and if you put it on your own laptop you have to be dangerously insane like this needs to go in its own little house or up in the cloud you put it in gcp and cloud run and you leave it there and you let it do what it does well it's the reason that uh mac minis are sold out yeah yeah yeah and anyway i have one here on my desk and and and cb literally you can't buy them because every this has become so popular and people are smart enough talk about no trust to know that you have to have a sanitized machine you can't just use it on your laptop with your various email accounts and your texting accounts and material on there …”
View more
Ridealong summary
OpenAI's latest tools, Nemo Claw and OpenShell, offer a corporate path for safer AI use, but they come with a hefty price tag. Users are spending up to $1,200 a year experimenting with these tools, often with no clear return on investment. This shift raises critical questions about the sustainability and security of AI in everyday applications.
“… servers, probably 50, 100K, plus 10,000 a month, 5,000 a month. Plus you needed a sysadmin to do all that work. All that got abstracted away. Okay, GitHub, you know, DigitalOcean, AWS, whatever, you know, you're going to use. but now this is different because those two or three first developers you're going to hire maybe okay yeah maybe we don't maybe we hire one but we don't yeah you don't need them at least not in the beginning right so that's a big c change and then what is the moat that's the other question everyone's asking right so it's like okay you back this company they're doing well but …”
“… of those big ticket items, Alex, that we used to negotiate $100,000, $200,000 for the lease of your office, two-year commitment. And, you know, it used to stand up 20 years ago, your own rack of servers in a co-location facility. So that was 100K in servers, probably 50, 100K, plus 10,000 a month, 5,000 a month. Plus you needed a sysadmin to do all that work. All that got abstracted away. Okay, GitHub, you know, DigitalOcean, AWS, whatever, you know, you're going to use. but now this is different because those two or three first developers you're going to hire maybe okay yeah maybe we don't maybe we hire one but we don't yeah you don't need them at least not in the beginning right so that's a big c change and then what is the moat that's the other question everyone's asking right so it's like okay you back this company they're doing well but you know i've had a couple of companies jason where they've gotten to 10 million arr and then somebody else comes along and does the same thing and it's like sort of game over. Yeah. And that never used to happen. So that's, that's sort of the other thing that everyone's thinking about. So we've been looking at a lot of infrastructure rather than …”
View more
Ridealong summary
The AI revolution has drastically altered how startups operate and how venture capitalists like Hustle Fund make investment decisions. With lower capital requirements and faster growth, the traditional role of venture capital is being questioned. This shift is prompting investors to explore new strategies, including a focus on hardware rather than just software.
“… and much more performant and much lower cost. So we've seen examples of like, if you, for example, connect PyDantic AI with code mode enabled to GitHub's MCP and you say, go and find the five latest pull requests. And I forget what the, what the question was, right. But the point was, we have to go jump through their API via MCP and calculate some value We seen tasks go from kind of down to 4 a result of using code mode Because one of the big reasons for that is that those MCP responses are vast. And so the NM has to put loads of tokens into context to go and pull out, well, actually, this is …”
“… is what people call programmatic tool calling or code mode, where instead of my LLM calling tools in a loop, sometimes using the return value from one tool straight into the next tool, the LLM can just go and write code and thereby be more reliable and much more performant and much lower cost. So we've seen examples of like, if you, for example, connect PyDantic AI with code mode enabled to GitHub's MCP and you say, go and find the five latest pull requests. And I forget what the, what the question was, right. But the point was, we have to go jump through their API via MCP and calculate some value We seen tasks go from kind of down to 4 a result of using code mode Because one of the big reasons for that is that those MCP responses are vast. And so the NM has to put loads of tokens into context to go and pull out, well, actually, this is just like the ID of the thing I need to make the next request. I just added an MPC server to talk Python a few weeks ago so people could ask questions about it and stuff. And what really surprised me is the actual return type that MCP servers recommend is markdown, not structured data. So you basically send a giant blob of markdown back as the …”
View more
Ridealong summary
Monty's Code Mode dramatically enhances AI performance by allowing LLMs to write code directly, bypassing complex tool calls. This approach not only reduces costs but also improves reliability, as demonstrated by connecting PyDantic AI to GitHub's MCP, where tasks were completed significantly faster. By simplifying data handling, Monty streamlines the coding process for AI applications.
“… win, win. That's my motto for the day. You won't know what might surprise you until you do. That's why it's a surprise. Surprise! SyFace found the GitHub repo for all this stuff. So I don't know if that means it's open source. I don't know if you could take the GitHub repo and compile it and make it do its job. Well, why not have it done for you? Yeah. Well, why not? Exactly. But it's kind of cool that they've put this all online. Yep. 41 repositories on GitHub under CYHY. Nice. So you can at least see what they're doing. That pretty cool It a lot of shell scripts is shell and Python Yeah it …”
“… and people who've been terminated and blah, blah. We don't know what equipment they left running and different configurations. You know, the more of that there is, the more chance that something unsuspected may be there. So win, win, win, win, win. That's my motto for the day. You won't know what might surprise you until you do. That's why it's a surprise. Surprise! SyFace found the GitHub repo for all this stuff. So I don't know if that means it's open source. I don't know if you could take the GitHub repo and compile it and make it do its job. Well, why not have it done for you? Yeah. Well, why not? Exactly. But it's kind of cool that they've put this all online. Yep. 41 repositories on GitHub under CYHY. Nice. So you can at least see what they're doing. That pretty cool It a lot of shell scripts is shell and Python Yeah it running on their infrastructure And I did get so I got that one report that had that one vulnerability Then a couple days later, I got a 34-page beautiful PDF that had charts and graphs. And it was tracking vulnerabilities and bar graphs. And how long has this been around?”
View more
Ridealong summary
You won't know what vulnerabilities might surprise you until you use CISA's free scanning service. This tool is essential for businesses with complex networking environments, as it uncovers hidden risks, even if it turns out you have nothing to worry about. With detailed reports and visualizations, it's a win-win for anyone responsible for network security.
“… that you're trying to fix yourself. First of all, God knows my blog would fit into that category. Sure, that's a good one. I built a synth. It's on GitHub. It's called AnySynth, and it's a little digital audio workstation because I wanted to. And it compiles to WebAssembly so that it actually kind of is running its own little C code in the browser. I'm working on a long-term project that I've neglected for a long time, extracting time-based data out of Wikipedia and aligning it with archive.org Wikipedia so that I can see big timelines of history with all the art objects and all the music that …”
“… founders who are like, what I want to do is build tools that let people build the kind of tools that are too small and too pointless for anybody else to make. So give me a list of those things for you that you're working on, your software woe that you're trying to fix yourself. First of all, God knows my blog would fit into that category. Sure, that's a good one. I built a synth. It's on GitHub. It's called AnySynth, and it's a little digital audio workstation because I wanted to. And it compiles to WebAssembly so that it actually kind of is running its own little C code in the browser. I'm working on a long-term project that I've neglected for a long time, extracting time-based data out of Wikipedia and aligning it with archive.org Wikipedia so that I can see big timelines of history with all the art objects and all the music that people made. That one's cool. That's going to be called unscroll.com. It's there now. It's just broken.”
View more
Ridealong summary
One developer is tackling the challenge of creating tools for niche projects that others overlook. From a digital audio workstation called AnySynth to a long-term project aimed at visualizing historical timelines via Wikipedia, these endeavors highlight the innovative spirit driving modern software development. This is a glimpse into the future of coding, where personal passion projects meet cutting-edge technology.
Top Podcasts About GitHub
The AI Daily Brief: Artificial Intelligence News and Analysis
3 episodes
Security Now (Audio)
3 episodes
Talk Python To Me
3 episodes
The freeCodeCamp Podcast
3 episodes
Practical AI
2 episodes
This Week in Startups
2 episodes
TBPN
2 episodes
The Real Python Podcast
2 episodes
Stories Mentioning GitHub
Best Podcast Episodes on Anthropic's Claude Leak
The source code for Anthropic's Claude AI has been leaked, unveiling potential future features and capabilities of the AI system. This breach raises concerns about intellectual property security and competitive advantage in the AI industry. The leak could impact Anthropic's strategic plans and influence the development of AI technologies.
Claude
Anthropic
Top Podcasts on Anthropic AI Code Leak
Anthropic has experienced a major leak of its AI codebase, which has revealed details about its upcoming models and features. This breach could impact the company's competitive position in the AI industry and raises concerns about intellectual property security.
Anthropic
AI code leak
Top Podcasts on Apple's Mac Pro Discontinuation
Apple has announced the discontinuation of its Mac Pro line, marking the end of an era for the high-end desktop computer. The company also hinted at the release of new iPhone and MacBook models, suggesting a shift in focus towards its more popular consumer products. This move could impact professionals who rely on the Mac Pro for intensive computing tasks.
iPhone
Apple
Mac Pro
MacBook
Best Podcast Episodes on AI's Impact on Jobs
Artificial intelligence continues to be a dominant topic, with podcasts exploring its profound effects on the labor market and the broader economy. Discussions range from the potential for AI to displace white-collar jobs and create new opportunities, to the ethical implications of AI-generated content and the emergence of an 'AI bubble.' The conversation also covers how AI agents are changing workflows and the race among tech giants like OpenAI and Google.