Cut LLM cost by 95%, replace ElevenLabs, and 10 top GitHub repos

0:00I've got a free tool that will make videos for you for free and claims to print money for you. PewDiePie, the famous YouTuber, says get rid of ChatGPT. He's got a free replacement and it's amazing. If everything that Claude designs for you just looks like everything Claude designs for everyone else, I've got a taste repo that will

0:16fix that and make things look beautiful. And watch out, 11 Labs, I have for you a simple way to create voices, clone your voice or anyone else's, and have AI read in that voice. So much more coming up today. Presented by Zapier, the AI automation company. All right, Peter, top 10 GitHub repos of the week. Starting with number one of the week is Money Printer Turbo. I don't know how I feel about this one, but I'll explain what it is. You go in, you type what you want a video to look like, you want it to sound like, and it will actually create the freaking video for you. And

0:51in many ways it is impressive, but once you get into the money printing thing, it feels like it's overhyped. I'm going to show it to you on GitHub so that you get a sense of what it looks like. I'll show you a video of how it works. And I've talked about this before, Peter. This is a way of creating what many people would call AI slop. Maybe I'm

1:08being too harsh about it, I don't know. What do you think about this? Well, I was hoping that it was just going to like print out money, you know, one of those money guns you get, but um unfortunately not. Um No, I mean, in terms of the overall project, it's actually quite well structured and it does what it says it's going to do. Um but the problem is, do people want to watch these videos? I guess that's the

1:29key thing in you as a video producer. It's like, do people want to watch this stuff or do would they rather watch someone actually do it for real? Um you are going to need a lot of bandwidth though if you download this repo. Um just because it has it's like 700 megabytes in size, I discovered. I actually cloned it. Um and it's full of

1:44fonts and samples and stuff like that. So, it's a big one. It's fairly easy to use too, though, once you do get it on your system, right? You just fill out a form or you just Yeah, there it is. You just give it what you need. And it creates it. Okay, maybe overhyped title, but maybe that's how you become

2:00number one. Yeah. Or but you need to plug in some API keys as well cuz it needs to use uh OpenAI or Deep Sea. It can It can support a whole different bunch of APIs, but obviously you are going to be paying for the the output from this. But it will also One of the cool things about it though is it will pull in um I don't know if you'd call it royalty-free, but kind of like free video that's on the web in certain repositories, and then it will integrate that into what it produces. So, it does some mildly clever stuff even if

2:27it isn't quite actually printing money. Okay. All right, maybe I'm being too harsh on it because it's promising a lot, but truthfully, if you can generate even B-roll like this and find it, I think there's value to it. Okay, that's number one for the week. Number two is Headroom. Your AI agents are burning through money reading junk, huge logs,

2:45bloated files, repeated search results. This sits between your agent and AI company and shrinks everything before it's sent, claiming 60 to 95% off your token bill with the same answers. Would you try this? What do you think of this? It's an interesting idea. I like the idea of putting a like a proxy in between um your agent and the LLM and then doing things with that kind of gap between to make the the communication more efficient. Just one thing I should pull up on though is that in that headline it says something like reduce your token bill 60 to 95%, which if you actually go into that they've got

3:21a page on their GitHub repo, which is actually a a real benchmark of what they've actually done with 50,000 different sessions that have run through this app, and the actual median saving is 4.8%. So, the headline is making it bigger than it is, but I mean I'll just quickly explain what it does just in a technical sense is let's say that your Claude code or whatever it is is sending lots of um log files or JSON or something over the wire, this thing will look at that and then and it down to a more minimal representation that the LLM actually needs. So, for a certain type of debugging session

3:57where there's lots of logs flying around, say, it may be able to reduce it by 60 to 95%. But, in general day-to-day use, um no, not so much. Um and that's by their own numbers. Would you actually use it? Is there a need for it? I don't think I use Cloud Code enough to need something like this.

4:15But, what about someone like you? Personally, I wouldn't trust it. But, that's just That's just me being, you know, critical of these types of things. But, you know, if it works for him, then great. I mean, there's people that would love this type of thing. Um I just would rather not have something sitting in

4:34between me and the LLM. Right. Right, especially for such little value. All right, let's go on to number three. Mark it down. This one I absolutely love. It is back from Microsoft on the top 10 list. What it does is it takes a PDF, a Word doc, a PowerPoint, Excel, whatever, and it converts it into markdown so that it's easy for you to to work with. It's easy for you to um to send to your agent so that you don't end up taking up uh so that you don't end up paying for a lot of tokens just to have your agent convert it. Uh I've got some examples of it here. You take a

5:08look at Actually, here, let's take a look Look, oh, this one I wanted to show. It even took this image on the right and it turned it into a description on the left. In this two-panel comic, a cartoon dog sits calmly at a table amidst, etc., etc. I like that it does that. I've got a short video here uh that I found on YouTube with someone showing how it works on a

5:28PDF doc. Look at how beautiful this is. I'm going to mute it while he explains it. my virtual environment. I've got a PDF here, just a doc PDF. And I can run this in my terminal. I'm going to run markdown doc PDF output md. That's it. It makes me a file automatically. We can open that file, and inside is sort of

5:49what we're hoping to expect here. Headings are clean, tables actually look like tables. Just works. What do you think of this one? Right, the real win about this, other than it being from Microsoft, is it's very extensible. And so, what I mean by that is that it's kind of like having one program that you can just throw any kind of like media or spreadsheet or word document or whatever, and then get out what the agent wants from the end of it. The actual value isn't in doing that conversion, because I mean, you can take any LLM and it will convert an image into some text. But, this is so that you

6:22can just throw stuff at one thing and get stuff out. The only catch with it is that by default, it uses um mostly Azure APIs for doing things like let's say you've got a scanned PDF, it will use an Azure API to do the conversion. Um however, because it is so extensible, you can write your own plugins for it, so it would use whatever you want. So, if you've got some magical way of converting, you know, an image into text or whatever, you can add your own

6:48plugins to this and build on top of it. So, it's kind of like a framework. Mhm. Um and I just like it from that perspective, that it's not just one tool for one job. It's like one tool that you can just throw data in, get stuff out, but then extend it with your own

7:00building blocks. You know, I freaking love the way that you explain these things. All right, let's go on to the next one. Oh, the next one is my sponsor. It's actually why I'm in a hotel room today. I'm here to meet with the founder of Zapier to talk about how we've been doing with them, and I'll tell you one of the things that excites me and why I think

7:14we've been doing really well. Peter, my problem is that I keep moving from like Claude to Codex to this to that, and I want to bring all of my tools along with me. I don't use Asana, but I do use Gmail, and I do use Google Calendar, and I give it access Notion, and so on. I want to be able to hand off all of these tools to whatever new thing comes out, and know that I both give it the power that it needs, but also have the restrictions that I want to to give it. And that's the beauty of this. The thing that I love about Zapier is

7:41they've now become, in addition to all the automations we know them for, they've become that trusted middle layer that lets me give permissions to my agents, but also restrictions. They cannot send email, they cannot delete all my files, and so on. Fair? Yeah, and actually it kind of ties a bit into that last item that we did in that it's something that sits in the middle, inputs, outputs. I mean, yeah, that's a common pattern actually with a lot of the

8:07projects we're covering. And a dependable company to do it, and not just for me, for people on my team when I want to protect them because they're not as deep into it as I am. All right, and because of Zapier, we're going to do a couple of honorable mentions here in the middle of the top 10. Number one honorable mention, I don't know why this does didn't make the list. This is PewDiePie. He created Odysseus. It's a ChatGPT alternative that runs on your computer. I think this is really creative. This is the guy who used to play video Actually, still I

8:33think does play video games on YouTube. Um, and here's his realization. He said, "Actually, here, let's have Let's play him with his realization." Crazy. The point is, you realize the model that you can run at home are amazing. The problem is the way you interact with the model, okay? Cuz I would at the time I was trying to self-host a a UI for it to get the same experience as I was paying my

8:56subscriptions for. And I should say this is because he's got these these LLMs that he realized he doesn't have to pay for, he can put on his computer, he doesn't have to pass his data outside of his own little universe, but it's really bad uh user experience to use it. these things that sort of come together and make this an amazing experience or

9:14it's completely missing. Where's my memory? Where's my deep research? What about the agent? What about all these simple integrations like webhooks? I got I I spent like 2 days trying to integrate that. So, that's why I started to build my own. And I thought it was funny as a meme. I'm like, "Look, I could be out

9:32there just building this." And then he did it, and it's actually really good. Just unfortunately too techy. Let me show people just a quick video of what it looks like on the inside. Um And I'm going to a message. Hello. This looks a lot like the cloud code experience. But check this out. the request. [snorts] It's going to give me a response in a

9:53second. say this is like the cloud chapter I use. I can see things like amount of context that's used. I can regenerate from here, rewrite shorter or explain simpler. Let's see how that works. Okay, so it's an in-place um I know this looks basic but let me show you this one cool thing too.

10:11which is nice. We can edit. Oh, interesting. We can edit the AI's response. I like editing the AI response. I was talking to Eric Reese who's got an AI project that also asks that also enables you to edit the response and he said it's because everything that is in a chat experience is context for the next response that you get. And he goes, "If you just let it have BS in there, it then uses it to understand." And so you want to edit. But that's a small feature that I liked. I will actually zoom in and show you on the left. It does way too much. It will do notes and tasks. It

10:43actually has um Where is it? It will do gallery, which then lets you edit [clears throat] photos. It's just it's very geeky in the most beautiful way. It's perfect for our audience. I don't think it's ready for the average user. What do you think of this? [snorts] It's an increasingly common thing to do. I mean, it's almost becoming like the the build-your-own blog system of like this decade. It's like, "Oh, build your own agent. Build your own harness. Build your own thing." And it's good to see someone that is as opinionated as PewDiePie doing it. I mean, I wouldn't necessarily use it because I don't necessarily have the same, you

11:18know, values or approach that he does. But I can see why he's doing it. Um and so it's very exciting to see cuz he's someone, you know, I think he's still one of the most subscribed channels on YouTube. Yeah, hundreds of millions of subscribers. So it's just fun to see what he does with that and you know, the wealth that he's got. Um and the fact that he's messing around in what kind of

11:37we're doing is uh really fun. Yeah, and you know, if you want to do if you do want privacy, and lately I think about all the medical stuff I send into Claude, I get it. It's good. Good tool. All right, next. G Brain, again, honorable mention heard on X. Uh this is Garry Tan building a permanent memory for his AI agents, then he gave

11:58it away. Uh and he's been adding more and more features to it. I think this is the from this week where he added voice, but I oh, wait. Where is it? Where is it? Uh here. Let me go right back here, cuz I want people to see what it looks like on the inside. And I've done an interview

12:13with the founder of the show. tab here in Alpha Claude, I can show you my brain here. You can see that we've got companies, we've got we've got people, for example, founders, Adam Guild here created the world's first AI CMO for restaurants. See, so what he's got is a really well-organized set of information on the people, the companies, etc. that he works with, and

12:38and the timeline of what they did. That's what this is about, making your agent smarter by giving it an organized database. Peter, thoughts? Um it's something that is very useful if you do have a lot of kind of disparate knowledge that you need to tie together in some way. So, when it's someone like Garry Tan, so he's the uh president of uh Y Combinator, for example. So, he's working with hundreds of different founders all the time, needs to kind of keep track of, you know, who's who and who's working on what, and that type of

13:06thing. Um I can see why brain would be useful. For me, I'm tend to be working on really like tiny tight projects where I kind of know what's going on, so it's not so useful for me. Um but this is an interesting project. Um you know, I think it is put together by AI, um but it's had some really good decisions behind it, so it's using um Postgres as the database, which, you know, a lot of people will like. Um and it's doing some interesting stuff like uh it's using embeddings um and BM25 ranking for looking stuff up. So, the there is some quality behind it, but I've not really

13:36poked into the middle of this brain. I've not done any brain surgery on it. Um, but yeah, people seem to be quite excited about this. They are. If you if you're working with a lot of clients, if you're if you're talking to a lot of people, and your agent needs to keep them all in order, this is a good way to do it. All right, uh next, this one you asked me to add

13:54on. This is uh Web Right by Microsoft. What is it? Uh it's another project from Microsoft, which I always like to see. Um, it kind of builds upon their work with a project called Playwright, which is basically a library that um developers have used in the past and still still now um to do testing on web apps most commonly. But you could also use it for scraping the web and stuff like that. It's just like a a remote

14:20control for a browser. The the problem they're trying to address here is that if you want to put an agent in control of a browser, you've got a few different ways you can do it. You can give it the access to the full screen view like some of these computer use things use now. But the problem with that is that while you get to see exactly what a user sees, you are looking at raw pixels, and that's quite demanding um in terms of the amount of tokens going over the wire and the speed isn't

14:45that great and so on. Um, whereas Web Right is much lower level, um so that a agent can just see like the different elements on the page, but a more technical lower level like um you would if you were programming something to remote control a browser behind the scenes. So, their goal here is just to make the whole thing more efficient and significantly faster and more token efficient in particular. Um it's very early days for this, but I'm excited to see where it goes just cuz again, it's from Microsoft and they've had a a lot of success in this area with

15:15Playwright already. And this is I actually can see the web browser as it's using it like in this demo that I just showed? Yes, but the but the agent behind the scenes is seeing more like the tree of kind of what's on the page. Right. So, it's not just it's not saying like look at these pixels and work out what's going on. It's more like look at the code and work out what's going on and

15:33then remote control it from there. Yeah, to create this document that I've been clicking through to show everything, um I had to go and find links. And what I did was I asked Claude to go find the links and I could see it saying, "Okay, I'm taking a screenshot. Now I'm understanding, taking a screenshot." That's what you're talking about. It eliminates it. And then the final heard on X, this is really popular on uh on X but not popular enough to make it to the top 10 list. It's uh

15:55Light Parse. What is Light Parse? I like this one just because it's a common task that we all have. We all have PDFs full of all sorts of things or we receive them. They're full of media kits and company data and all this type of stuff. Um and we need to work with them. And sometimes they have very weird formats and layouts to them. Um so, you know, it'd be lovely if we could have everything in markdown, but sadly we can't. Um so, PDFs will often be in columns or they'll have different tables in and things like that. This is something that, you know, without using

16:26AI can break down some of that stuff. Um and we've had, you know, there's tools that can do OCR and stuff in the past. It's just nice to see something that brings together the OCR and, you know, being aware of layouts and how to process PDFs that we can run entirely locally without, you know, having to shovel all of our PDFs up to, you know,

16:44Opus or OpenAI or whatever. And it's on on my desktop, doesn't need to have outside connection, and it just works. Yeah. Okay. Excellent. So, unlike the other one that we saw, which does need API, does need outside access, this is light, it's on my computer, works. Okay. Let's go on to the next one.

17:04Compound Engineering plugin from Every. I like Every. This is a company that both makes software and writes content about how to make software with AI and how to use AI. I I like it. What is this though? Um I mean I like every as well. They do some great work and they have so many different weird random little projects and services out there. I think you said you said you used one for looking at your email and stuff like that. And the design that they have is amazing as well. This is largely a giant set of skills which tell you all kind of instruct Claude and Codex. And they the

17:41way they've coded it is actually kind of cool because it actually plugs into almost any of the main sort of you know harnesses. And it includes things like you know how to do good get commits. It includes things like even how to program Ruby on Rails the DHH way. And the thing I like about these types of repo isn't necessarily just to install them and just roll with it because I don't necessarily like other people's opinions to take over how my agents work. But I like to dig in and actually look at what the skills are and see is there anything in these skills that I can use? Um and I provided you

18:13special access with the directory to show you what those skills are. And it covers all types of things. Um you know from front end design skills to how to think about projects and stuff like that. I like to dig through these and see if there's any Yes. This is This is gold where it is. It's under plugins then compound engineering and skills you showed me before we got started. And then in here I can actually see the skill. And what you do is you look through and you say, "Okay, how are they thinking about this? How are they thinking about uh commit? How are they thinking about each one of these and

18:41debugging?" And that's what you want out of it. Absolutely cuz I don't necessarily want to trust someone with a bunch of rules and then just have them put them into my system and I don't know what they are. I need to look at them anyway. So I might as well learn from the skills rather than just blindly trust them. And that is actually quite relevant for one of our future items that we're going to cover. So uh you know, you can't just blindly trust skills just jammed into your context

19:02from my perspective. And I've got a video here that I'll include in the in the report that everyone can get in the description where you can see one of the founders within the every uh community going through and explaining how this works, how he uses it, how they think about compound engineering. All right, I'll let you all watch this afterwards. On to the next one. Stop Slop. This is again, last week it was on number it was top 10, this week it's top 10. And what it does is it says, "Look, we all know when AI writing is AI writing. There's certain tells. Why don't we just tell

19:36the AI to stop using these tells?" I think a great example of it is right here, actually not this one, the live demo where they said, "Look, these are the things that we know. Like starting off with here's the thing." Just get rid of it. It turns out just get rid of it and there's a few different things that it will eliminate. Would you use this for

19:56writing? No. Um this is the one No, this is this is the one that I was foreshadowing actually when I said about just don't trust skills straight out of the box. You need to write your own one of these and the problem with Stop Slop in particular is there's almost nothing there. Like if you look through the the documents, it's absolutely tiny. It It's just a bunch It's just like a bunch of small rules and some of them are very bad. Um so for example, there's one rule in it that says, "If any sentence starts with a question that starts with WH, rewrite it." So you can't start sentence

20:28with what or where. Um it says, "Any adverbs, kill them." Well, adverbs can be bad, but I wouldn't necessarily say just get rid of every single adverb. So I would look at this skill um and say, "Yeah, I want to take this. I want to take that." But I wouldn't just use it blindly because it could just completely neuter, you know, your voice and your writing anyway. I mean, I know this is to process AI writing, but you know, do you want to take everything

20:55out of it? Yeah. Uh it's okay. I'm in a hotel and I guess check out is at 10:00 because they just came in to clean up in here. I didn't know. I'll talk to them later. we were getting a nice steak delivered. Where did you Where did you even see that? The WH part? Uh if you go into skill.dot I think it

21:16was No. Actually, the skilled MD just replies just responds to the other skill files. Um I don't know where it was. I just wrote down notes when I was reviewing it. Okay. Um but it's in one of those markdown files. But so yeah, it was just like get rid of this and get rid of that. Um there are other ways you can look into this. Just to let you know. So, anyone that's watching this, if you Google for Wikipedia signs of AI writing, there's another really good document that Wikipedia has put together, um which also has tons of telltale signs which you might also want to turn into your

21:46own skill file. I see. So, you're saying create your own skill file, don't just use theirs, and you can you can use theirs as reference, but not right out of the box. Huh. All right. I like of course models keep changing. So, you know, you might be using a model tomorrow. You might be using Opus 4.9 or GPT-6 or whatever it is, and it might have these different tells. Well, that old document isn't going to work. So, you need to keep on top of it for

22:10yourself. Okay. All right. I like that warning. Next is super memory. Um every new chat with Claude or ChatGPT is like meeting a brilliant employee with total amnesia. You're re-explaining everything every time. This gives your AI a long-term memory follows you across every tool. Um What do you think of this? And I've got someone here, uh Ben Sigman, who actually evaluated this compared it to others. What do you think of this before

22:36we go into his evaluation? I have not tried this, but it does take us back to the G brain item somewhat in terms of how it works. Um the big thing that super memory is doing, which is a bit different, is that they're running it as a commercial service. So, it's a lot easier for people in companies or whatever just to plug in and use it. But you can also use it in the open-source form uh for free, too, which is nice. So, I like the way they've structured it from that that perspective. Um but again, in terms of actually using it, it's not a sort of

23:03thing I necessarily would use just because I have my memory structured already in a in a different way, but they look very slick. How do you avoid the total amnesia and or just like one time it knows it, the next time it doesn't? I like to start my sessions with the amnesia because I like to point it to

23:22things that we've done before as we go. I don't like to just say, "Just here, have access to everything. Just go at it." I like to be selective about what I give it because I don't like it when So, like even something like Claude or ChatGPT, I don't like it when I ask a question and it uses my prior memories as like, "Oh, why are you asking that question? Because previously you did X, Y, and Z." And it's like, "No, I'm asking this independently of what I previously discussed with you." Um, so I

23:48don't want that in my coding either. All right, fair point. I've got a video here explaining how it works. I'd like your feedback on it. Let's go on to the next one. Um, ECC. This is a builder who spent 10 plus months living in AI coding tools, packaged everything he learned into 63 specialized agents, 249 skills into one free install. It's the closest thing to an operating system for your AI coding assistant. It's got Does it really have 205 stars? And it's one of the biggest

24:16repos on GitHub. Does it? Does it? It Yeah, it's even more than 209 now. Yeah, and 31,000 forks, and still you have a controversial point of view on this. What is that? Also, did you Actually, I'm I'm sorry. First explain Explain it in your words. What is this? And then what's your what's your thought on it?

24:37It's a giant pile of stuff. Um, yeah, I'm not going to use any offensive terminology. This is clearly, you know, someone has has spent a lot of time on this and put something together. Problem is it's just too much. It's like, you know, wheeling in a Boeing 747 or something just to, you know, cross

24:52the street. Do you Do you trust it? Are you going to read for all of it? Now, clearly there's enough people that are lazy enough that they're just going to go, "Oh, great. Loads of stuff. Download, click, star, and everything." But, the fact is I have no idea what any of this is doing or what it's been directed to do. So, why am I just going to trust it out of the gate? Now, the thing about the the one that Every did earlier is that at least with Every you can trust them. They they're You know who they are. They have a established background, and they are

25:20experts in using this stuff. But, how am I going to trust this to know how to review Go code or Java code or Python code without going through it? And then by the time I've gone through it, I might as well have made my own. So, I don't see the appeal of these types of

25:31things. It's too much all at once. I don't either. I could see him wanting to share and other people maybe wanting to learn, but it's just a lot a lot of information in here. A lot of different tools. I've got a video of somebody here actually using it. I'm going to I won't even play the whole thing, but I'll give people just a taste of Actually, I don't even think it's worth even the taste of it. You'll have the

25:53video, so you can watch it on your own. Basically, what he said was he said, "I want to add a uh calendar link to my site where people can book meetings with me." He I don't know why he needed the skill in order to do it, but he used the Everything Claude code plan. He planned it, and he got the Calendly integration

26:11in there. Again, there are some these things are great. I think these things are great for the people that made them because they made them the way they want them to make them, and they use like their their own Like the your If I took my approach and put it into a set of skills, then it works great for me. Doesn't necessarily work well for someone else. So, you really need to review these carefully

26:30before you go whole hog on it. There's the Calendly. Yeah, I agree. Okay. Next. Um And I [snorts] I do think also it's nice to look over somebody's shoulder and see how they do things. See how they structure things. Yeah. But, like you said, just using it right out of the box, no. I like this whole style here. Here's the

26:49problem that Taskade addresses. We now see every time somebody gives us a document that they think looks beautiful, we see that it looks just like Claude because they're using the Anthropic design. It drives me freaking crazy. Honestly, I'll be honest with you, Peter. These like web pages that you're all looking at right now, these all looked exactly like Claude. What I did was I couldn't stand looking at them after the first time. I then made some adjustments myself and then I saw a repo in one of our past sessions which said you can take designs from all these

27:18other companies and use them. So I did. This is from Intercom, the the the software company. I used their design and then I changed the colors to make it feel like mine and it worked and it made it feel a little bit better for me. I'll probably keep tweaking it. And what I like about this is that it's doing the same thing. It's saying use this to change your designs. We've got a few We've got a Here, there's a video of a creator who tried it and he's going to show what the designs look like and it's of course on the GitHub repo also. What do you Here it is. Look, this definitely

27:48doesn't look like Anthropic's design taste. No. What do you think of this? This is an area where I'm a little bit more inclined to go along with, you know, having a a bunch of different skill files brought into a project. And the reason for that is that because it's about taste rather than how to do

28:05things. Mhm. And so I don't mind other people's opinions necessarily being brought into design if you like the output. Cuz the thing is like if you don't like what it produces, you can say oh screw that and then let's go with a different approach. Right. So this this project does build upon previous kind of steps forward in this area like impeccable.style which I saw actually in the screenshot for that video. Um [snorts] is another thing. But the thing is once you design with these skill files, often you will then start to see the same like tropes coming out over and over and over. So again, this

28:39is a situation where I think it's good to see what other designer's taste is but then build on it for yourself. Build your own things like this. Um and you know, the models now are actually so smart you can even do cool things like if you see a photo that you like, so for example, I took a photo the other day of the backrooms, you know, that's big at

28:56the cinema at the moment. And I said, "Design a web page that looks like the backrooms." and threw it into Opus and it did it. And it's like, "Oh, actually this is kind of cool." Like it's got the color scheme and you know, all this type of thing. You can do that now. So, you can just find an aesthetic that you like, throw it at a model and just do it. You don't necessarily have to say "Design this whole thing from scratch for me." You can give it inspiration. But if you want to mix in things that, you know, give you like skills like this that give ideas on

29:21typography and fonts and stuff like that, blend it in, give it a try, see how it goes. You know, I think these things are kind of cool. I do too. I like them for just seeing a different take on what I'm already doing. All right. Yeah. Next. Understand anything. Here's the deal. Maybe you created something a few months ago and you forgot what you got there or maybe you started a new project and you're looking at something for the very first time. You've got hundreds of thousands of lines of code. You don't know what anything does what anything does, what it means. What this will help

29:50you is understand it by turning it into a visual that lets you see what's what. That's what understand anything is. What do you think of this? I've not used this one, but it does plug into an idea that I've had for a while now which is the try and avoid using LLMs for writing too much and focus on using LLMs for reading things because they are much better at that job. So, I would be much more likely to take a bunch of skills or you know, plugins like this and have it process something that already exists because it can extract insights from things perhaps better than it could

30:25recreate that thing. Um so, yeah, I have absolutely no problem with projects like this and there is a lot to reading large code projects that you can't just go to, you know, Codex or Claude and say, "I'll read this project and tell me X Y and Z." Sometimes there is a lot of analysis to be done um on top of it and if these skills give it the extra power to get over those hurdles, then it could make the analysis even better. So, yeah, but again, I've not used this one, so I don't know how well it does, but a lot of people seem

30:55to like it. There's a little bit of controversy here on Hacker News. What what could people be upset about with this? Uh was there a thing about yes, someone was saying that the stars might not be entirely legit, which is a common problem on GitHub. You know, there's this whole thing about that you can pay

31:15to get your repo starred. And, you know, the reason for that is that it's the modern version of kudos. You know, it's if your repo has 10,000 stars on it, then it must be better than the one with 100. It's not necessarily true, but it is a you know, it's a hurdle to overcome. I don't know anything about this project and whether it's done that, but that is something that I think people in that Hacker News thread were

31:36thinking might have happened. I think we need a better solution for this. We need something like what do people who I care about think of this or how many of the people who are creating give it star? I don't know, something. Digg is is messing with this a little bit, digg.com. I don't think anyone's nailed it yet and it's bothering me and it's hurting the

31:55whole ecosystem. This one you love. You actually told me Android Studio. Yeah, Vox CP M. What is it? Okay, so we've had a load of text-to-speech things over the years all the way from the '80s where we had like, you know, robot kind of voices through to the sort of systems that Stephen Hawking used, but then in the last 5 to 10 years, you know, AI has really turned that dial up from like a two out of 10 quality to sort of eight

32:22out of 10. And this is actually pretty good. You know, at first it I was saying 11 Labs quality, like that's what they're claiming. I would say it's not quite there, but it's like 95% of the way to that. And it was so good, actually, I could run it on my own Mac. Like, it downloaded, compiled, downloaded the model, and I was up and producing audio

32:44with this, you know, within 10 minutes. And the output's not bad. And the good thing is you can sculpt it as well. So, you can say, "I want a voice that sounds like XYZ." And it will do that. I'll do it right here. Old man with raspy voice. And then I could have him say, "Get off my lawn." And this is not working right

33:06now on uh on Hugging Face. Uh, but you get a sense of how it is. You can also upload your own uh voice as a reference and allow it to take off from your voice. I've got a video here to show how it works. Um, it's it's been amazing. I don't know how Eleven Labs is going to compete when all this stuff is so is so free. It's becoming so accessible. People are are able to use it, like you said, on their

33:30own computers, super easy. What do you think? What I don't know where Eleven Labs is going to go with this. And So, well, the one thing that Eleven Labs has going for it is that they've really focused on having um professional voice actors actually supply their voices with permission, with licensing. So, that's the win there is that companies that want to have voices that every single legal thing is ticked and crossed can go to Eleven Labs and they provide that kind of compliance side of it. Um, it's not necessary just about producing speech. It's about producing a paper

34:03trail. Which, you know, actually, I didn't realize I just sounded like Claude then, the way that I explained that. Um, but that is basically what it is. Yeah, exactly. [snorts] Um, so, you the thing is, you know, if you produce audio with this, it could be cloned from anyone's voice and, you know, Right. you know what your system's doing in the background? You know, it may have downloaded a video of, you know, some famous politician and just cloned a voice for you without knowing it. So, yeah. Eleven Labs isn't going to let you

34:26do that. Here, let's have play on this video, which of course we'll have in the report for everyone who wants it. Vox CPM is an innovative end to E beyond the ancient oaks and the misty trail. A secret remains on I'm convinced that Dan from Smart Tutorials on this video is actually just a voice using Vox CPM. Listen to this. Like look at this. I actually think that

34:48he that this is not really him. Today, we are diving into Vox CPM. I don't know. I don't know. I'll let people decide for themselves. All right. That is number 10. We've got the full report in the description so you can play with this, listen to it, try it yourself. And Peter, where do

35:03people see you? You can find me on Twitter. Oh, that's not Twitter now anymore. It's X, isn't it? Cooper X86 um or PeterC.org on the web. And of course, we'll have a link below. And now that you've listened to this, we've got 10 other repos that were super hot last week plus three special ones that you've got to see. There's a link right here on the screen. Click it and

35:21we'll see you over there.