Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

🎉BERT Semantic Interlinker App V2 (Free App)🎉 Free Streamlit App to Semantically Interlink Pages using Sentence Transformers. Last week Emilia tagged me in this excellent article that she had linked to the original version of the BERT Interlinking App. I checked the stats and over it had 17,000 unique... visitors with no promotion at all. I spent the last week re-writing it from the ground up with a ton more features, visualisations and polish. What's the Point? “There are tons of page Interlinkers out there, why not just use those?” It’s a fair point, this script doesn’t even use anchor text or link metrics when making recommendations. What it does differently is make logical connections to pages that will please your users and increase revenue. (link to related helpful content). Take the Page 'HP Original Ink' Using this interlinker it'll match to the following related pages: 'Printer Ink' 'Printers' 'Printer Paper' Even thought syntactically those words are a million miles away from each other. I originally wrote it to surface User Guides / Buyer's Guides at a category level. But realised there are so many other uses for it. ✅ Interlink Related Products Within Category Text ✅ Show Related Categories ✅ Surface Related Content to Assist Conversion (Blogs, Buyers’ Guides, etc.) ✅ Display Products Most Closely Related to Category Page for Increased Relevancy ✅ Feature Related Blog Posts If you haven't tried it before I'd love you to give it a go, if you have tried it before you should revisit it as it's been completed overhauled. (The original version actually had a bug that prevented a large number of results from being returned 🤦‍♂️) Full Write Up with New Features Instructions: Direct Link to the App: Retweets for reach most appreciated!show more

Lee Foot 🐍📈

10,725 subscribers

34,701 views • 2 years ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

Lee Foot 🐍📈2 years ago

@me__emi__ Looks like this is getting the hug of death. Just message and I'll reboot. I don't think @DataChaz is around at the moment to ask for more resources. cc. Maybe @streamlit can help :)

Andrea Volpini2 years ago

@streamlit @me__emi__ Super excited to review this new release!!

Suganthan Mohanadasan2 years ago

@streamlit @me__emi__ Great work as usual Lee.

Lee Foot 🐍📈2 years ago

@streamlit @me__emi__ That means a lot coming from you. We should have SaaS'ed it 🤣🤣🤣

Viacheslav Varenia 🇺🇦2 years ago

@streamlit @me__emi__ I'll have to give it a try.

Richard Hearne2 years ago

@streamlit @me__emi__ Lots of polish. Well done @LeeFootSEO!

Ecommerce Optimizer2 years ago

@streamlit @me__emi__ Awesome Lee

Svet Petkov2 years ago

@streamlit @me__emi__ Mind blowing! Great work @LeeFootSEO

Jan Builds Digital2 years ago

@streamlit @me__emi__ Could you pinpoint a website crawler that allows downloading a compatible crawl file? I cannot do it my current Ahrefs package.

Lee Foot 🐍📈2 years ago

@SaaSBuilder94 @streamlit @me__emi__ Sure, it's set to use @screamingfrog by default. They have a free version that supports up to 500 URLs.

Related Videos

I really like 's interactive landing page My favorite landing pages are the ones that drop you straight into the application and let you use it, you barely see that though I think it makes sense because why would you even need to sell to a customer with a big sales-y landing page if your product is impressive enough to convince them to buy it just by using it? ElevenLabs does a great mix of being able to actually use all the basic features as a demo while still being a traditional landing page This is easier with sites like Nomad List, because people just browse cities and it doesn't cost me much, but it's much harder to do this with AI apps because they cost a lot of money for every time you generate something (like photo, audio or text). One idea I had for Photo AI is to pre-generate a lot of combos of photos then on the landing page make a little demo and let them choose default models (like white man, black woman, etc.) and prompts etc. Then I just pre-gen all those combinations (like 10,000 pics, maybe $100) and I can have a demo on the landing page Unaffiliated with ElevenLabs btw, just like the website!

I really like 's interactive landing page My favorite landing pages are the ones that drop you straight into the application and let you use it, you barely see that though I think it makes sense because why would you even need to sell to a customer with a big sales-y landing page if your product is impressive enough to convince them to buy it just by using it? ElevenLabs does a great mix of being able to actually use all the basic features as a demo while still being a traditional landing page This is easier with sites like Nomad List, because people just browse cities and it doesn't cost me much, but it's much harder to do this with AI apps because they cost a lot of money for every time you generate something (like photo, audio or text). One idea I had for Photo AI is to pre-generate a lot of combos of photos then on the landing page make a little demo and let them choose default models (like white man, black woman, etc.) and prompts etc. Then I just pre-gen all those combinations (like 10,000 pics, maybe $100) and I can have a demo on the landing page Unaffiliated with ElevenLabs btw, just like the website!

@levelsio

255,806 views • 1 year ago

GameDay Insights Hitting Props Overview (one of the main Homerun/baseball sites that cappers in this space use) Here’s the rundown on how I use it to research hitters and answer most common questions. I took maybe 3 minutes at most using this exact process to cash a +2000 ticket yesterday—once you know what to look for, it barely takes any time. There’s no for sure method, so experiment to find what works for you! If any questions or want more videos/ livestreams on different topics just hmu. I’ll keep everything in the “Guides” page mentioned for easy access. Basic guides for anything baseball related is there for free!! - code: "GDI25" for 50% off 1st month

GameDay Insights Hitting Props Overview (one of the main Homerun/baseball sites that cappers in this space use) Here’s the rundown on how I use it to research hitters and answer most common questions. I took maybe 3 minutes at most using this exact process to cash a +2000 ticket yesterday—once you know what to look for, it barely takes any time. There’s no for sure method, so experiment to find what works for you! If any questions or want more videos/ livestreams on different topics just hmu. I’ll keep everything in the “Guides” page mentioned for easy access. Basic guides for anything baseball related is there for free!! - code: "GDI25" for 50% off 1st month

🥷

132,840 views • 1 year ago

I downloaded this app so you don’t have to. Politics aside, this is an incredibly horrible app that feels so bad it couldn’t have even been vibe coded. The app launches to a very loud and bright (and compressed) video explaining what the app does. There are 5 different font families throughout the app. The article viewer is just a WKWebView but has a custom scroll view (why?!). Every header is sticky and opaque for no reason. Opening a tab for the first time in a session flashes a white screen. Looking up anything just shows “why the democrats are evil” type stuff about anything that might show the Republican Party as negative. The app constantly freezes. Every button takes about a second or two to load the content before doing anything visually (like switching tabs). This app does not understand safe areas. Without any animation it randomly kicks you into a full screen view asking to enable notifications. The header shrinks slightly when animating for no reason. If the content doesn’t expand beyond the screen height (like a failure to load) then it will just jitter. There is no color contrast. No color even makes sense.

I downloaded this app so you don’t have to. Politics aside, this is an incredibly horrible app that feels so bad it couldn’t have even been vibe coded. The app launches to a very loud and bright (and compressed) video explaining what the app does. There are 5 different font families throughout the app. The article viewer is just a WKWebView but has a custom scroll view (why?!). Every header is sticky and opaque for no reason. Opening a tab for the first time in a session flashes a white screen. Looking up anything just shows “why the democrats are evil” type stuff about anything that might show the Republican Party as negative. The app constantly freezes. Every button takes about a second or two to load the content before doing anything visually (like switching tabs). This app does not understand safe areas. Without any animation it randomly kicks you into a full screen view asking to enable notifications. The header shrinks slightly when animating for no reason. If the content doesn’t expand beyond the screen height (like a failure to load) then it will just jitter. There is no color contrast. No color even makes sense.

Ethan Lipnik

79,708 views • 3 months ago

Imagine an AI application that can type anywhere you can and use the full context of what's on your screen. This is the application we all deserve (at least if you have macOS.) Check out Omnipilot. It's an app that works with every other macOS application and uses Claude Sonet 3.5 in the background—it also supports Gemini and GPT-4o. Here is the idea: You can use the tool to ask questions about anything on your screen. Or you can use it to autocomplete the text you are typing. You don't need to copy and paste anymore or waste your time providing context to a model. It sees what you see. It works right where you are. That's pretty cool. Here are a couple of cool examples: • Use it to reply to an email • Use it in the terminal to autocomplete a command • Use it to finish a document • Use to send a message on Slack AI at the system level is bonkers. You can read a ton more on their Product Hunt launch page: Thanks to the Omnipilot team for collaborating with me on this post!

Imagine an AI application that can type anywhere you can and use the full context of what's on your screen. This is the application we all deserve (at least if you have macOS.) Check out Omnipilot. It's an app that works with every other macOS application and uses Claude Sonet 3.5 in the background—it also supports Gemini and GPT-4o. Here is the idea: You can use the tool to ask questions about anything on your screen. Or you can use it to autocomplete the text you are typing. You don't need to copy and paste anymore or waste your time providing context to a model. It sees what you see. It works right where you are. That's pretty cool. Here are a couple of cool examples: • Use it to reply to an email • Use it in the terminal to autocomplete a command • Use it to finish a document • Use to send a message on Slack AI at the system level is bonkers. You can read a ton more on their Product Hunt launch page: Thanks to the Omnipilot team for collaborating with me on this post!

Santiago

72,306 views • 2 years ago

F it, full automated money making now on Larrybrain. I have released the app template I use for Snugly that generated me revenue without touching anything on Larrybrain. The template gives your agent ideas of what the app can become and how to create it. Most importantly, it will give your openclaw agent full context of your app to automate your marketing with Larry's viral marketing skill - now used by over 5500 agents. It is my entire playbook from app, to marketing all the way down to revenue generation. All you have to do is ask your agent "install the larrybrain skill please" Or click the link in replies. Then ask to use the Larry marketing skill with the AI Image App Template. As always, the best part about any of the Openclaw skills is they are not a black box. This is just a template, you can rip it apart and customise it how you want. The key is to show you what is possible with these skills and how you can start to use the power of larrybrain and the context of knowing about the different skills to build extremely powerful and useful tools. This is the first skill specifically designed to work hand in hand with another. To note as this confuses a lot of people: Larrybrain doesn't download the entire marketplace once installed. It just is aware of everything on the marketplace at all times, so when you ask it questions, it can search and find the best skills for you to achieve your goals. When you download some skills, like this new AI image app template, it is aware of the larry marketing skill to help it reach it's full potential. Larrybrain will not install skills without you asking it, just like on Clawhub. No information you add to any of the skills gets sent back through Larrybrain, this is all hosted locally and communicated between you and whatever endpoint you are using. It is a powerful marketplace tool to help enable you to reach your goals. Link below.

F it, full automated money making now on Larrybrain. I have released the app template I use for Snugly that generated me revenue without touching anything on Larrybrain. The template gives your agent ideas of what the app can become and how to create it. Most importantly, it will give your openclaw agent full context of your app to automate your marketing with Larry's viral marketing skill - now used by over 5500 agents. It is my entire playbook from app, to marketing all the way down to revenue generation. All you have to do is ask your agent "install the larrybrain skill please" Or click the link in replies. Then ask to use the Larry marketing skill with the AI Image App Template. As always, the best part about any of the Openclaw skills is they are not a black box. This is just a template, you can rip it apart and customise it how you want. The key is to show you what is possible with these skills and how you can start to use the power of larrybrain and the context of knowing about the different skills to build extremely powerful and useful tools. This is the first skill specifically designed to work hand in hand with another. To note as this confuses a lot of people: Larrybrain doesn't download the entire marketplace once installed. It just is aware of everything on the marketplace at all times, so when you ask it questions, it can search and find the best skills for you to achieve your goals. When you download some skills, like this new AI image app template, it is aware of the larry marketing skill to help it reach it's full potential. Larrybrain will not install skills without you asking it, just like on Clawhub. No information you add to any of the skills gets sent back through Larrybrain, this is all hosted locally and communicated between you and whatever endpoint you are using. It is a powerful marketplace tool to help enable you to reach your goals. Link below.

Oliver Henry

110,044 views • 4 months ago

I know we wanted to announce a roadmap tomorrow, but feeling good about it now, so just going to share what’s coming to the app soon. The bullets below are the first things coming, treat this as the initial $jellyjelly coin integration roadmap. Note: Had breakfast with walkerguffey from Hello Moon this AM, engineering resources are locked in. The MVP is as follows: * inside the JellyJelly app you’ll see a place on your profile to connect and prove ownership of $jellyjelly * once proven, there’ll be a badge on your profile, and it will unlock the premium App usage, and give you the ability to customize your username * Inside the app, you’ll be given a $jellyjelly coin wallet. If you have the coin you can send money to that address for use within the app ecosystem. * tip a creator you love/ support $jellyjelly for their jellies from their profile This is what we’re building towards, and it will lay the foundation for rapid iteration. Thank you for your support. Please stay patient as we build these features.

JellyJelly: Human Social!🪼

71,750 views • 1 year ago

More moves to AI-first living. Got the Genspark browser that just came out. One thing I notice is that I like having separate browsers working on different tasks. I'm not a big user of MCPs, since I'm not really a developer. Are you? They have a store of a bunch of MCPs available to use. Most of my AI work is research related, or answering emails and scheduling things, I'm focusing more of my effort there. Genspark has been shipping a ton of stuff the past few weeks, from ability to make slides to a new AI secretary that can schedule things, or help you answer your emails. First I looked at, "does it make sense to move over to this new way of working?" The problem with that is you gotta learn a new browser. Well, it looks like Google Chrome, except it has a prompt window. Click the icons underneath it and you will see you can add X, Notion, Google stuff like calendar and gmail, or a variety of others. But the real power is just talking to it. I asked it what kinds of tasks it can do, and it answered: "Just tell me what you want to accomplish! For example: "Research the latest developments in spatial computing and create a presentation" "Analyze my Gmail for any important emails from this week" "Find information about AI robotics companies and create a spreadsheet" "Generate a video about emerging tech trends" "Help me plan a trip to CES 2026" And so further into AI-first living I go. Have you tried it yet? What do you suggest I do next to use more AI to run my life and build my business? I have another browser tab building a video for me. What a beautiful time to be alive. Download it at:

More moves to AI-first living. Got the Genspark browser that just came out. One thing I notice is that I like having separate browsers working on different tasks. I'm not a big user of MCPs, since I'm not really a developer. Are you? They have a store of a bunch of MCPs available to use. Most of my AI work is research related, or answering emails and scheduling things, I'm focusing more of my effort there. Genspark has been shipping a ton of stuff the past few weeks, from ability to make slides to a new AI secretary that can schedule things, or help you answer your emails. First I looked at, "does it make sense to move over to this new way of working?" The problem with that is you gotta learn a new browser. Well, it looks like Google Chrome, except it has a prompt window. Click the icons underneath it and you will see you can add X, Notion, Google stuff like calendar and gmail, or a variety of others. But the real power is just talking to it. I asked it what kinds of tasks it can do, and it answered: "Just tell me what you want to accomplish! For example: "Research the latest developments in spatial computing and create a presentation" "Analyze my Gmail for any important emails from this week" "Find information about AI robotics companies and create a spreadsheet" "Generate a video about emerging tech trends" "Help me plan a trip to CES 2026" And so further into AI-first living I go. Have you tried it yet? What do you suggest I do next to use more AI to run my life and build my business? I have another browser tab building a video for me. What a beautiful time to be alive. Download it at:

Robert Scoble

84,349 views • 1 year ago

After months of stealth work I’d like to finally introduce my new app to the #ICPFamily! This app lets any user create a personal asset canister that only they own using just a wallet. It also provides a file explorer in the browser to let users upload and manage their files on chain. Features: • Code-free autonomous canister creation. • Familiar file explorer interface. • Drag and drop file upload. • Supports Plug, Stoic, and NFID. • Works on mobile with NFID. The app is currently in a whitelisted beta as I finish up testing but I’m happy to allow anyone early access. There are a lot of features still on the way including share via QR-code, named canisters, and even automatic cycles top-up. This app was meant for everyone to be able to use so I look forward to hearing everyone’s thoughts, feedback, and feature requests. The link to the deployed app is below, just login and dm me the principal at the bottom for whitelist :)

After months of stealth work I’d like to finally introduce my new app to the #ICPFamily! This app lets any user create a personal asset canister that only they own using just a wallet. It also provides a file explorer in the browser to let users upload and manage their files on chain. Features: • Code-free autonomous canister creation. • Familiar file explorer interface. • Drag and drop file upload. • Supports Plug, Stoic, and NFID. • Works on mobile with NFID. The app is currently in a whitelisted beta as I finish up testing but I’m happy to allow anyone early access. There are a lot of features still on the way including share via QR-code, named canisters, and even automatic cycles top-up. This app was meant for everyone to be able to use so I look forward to hearing everyone’s thoughts, feedback, and feature requests. The link to the deployed app is below, just login and dm me the principal at the bottom for whitelist :)

Daniel

113,776 views • 2 years ago

Some Muslims have been calling me a liar for this tweet I made. This is the records of my chat with my friend, I intentionally showed other parts of our chats not related to this so you will not say I am texting myself. When I tweet, I do so with consciousness about the fact that there are people here that know me personally. People as far back as high school, med school and even those I have had worked with at several point. While Taqiyya is permissible in your religion, it would be foolish of me to lie in order to make a case for my faith as I would not be excused for such.

Some Muslims have been calling me a liar for this tweet I made. This is the records of my chat with my friend, I intentionally showed other parts of our chats not related to this so you will not say I am texting myself. When I tweet, I do so with consciousness about the fact that there are people here that know me personally. People as far back as high school, med school and even those I have had worked with at several point. While Taqiyya is permissible in your religion, it would be foolish of me to lie in order to make a case for my faith as I would not be excused for such.

Kunle

89,431 views • 4 months ago

I think I discovered the cheapest way to code with AI 😁 I tried GLM 4.5 on Claude Code and I'm really amazed how good this model is! I usually test with my nextjs crm app benchmark so I asked it to do that. Prompt "create a nextjs app which is a crm app. use sqlite for the database and use api routes to manage connecting to the database from the frontend" My observations - Generation feels like Sonnet 4 intelligence - Speed is great - It used create-next-app so it bootstrapped nextjs v15.5.2 - It created a sqlite database and used Prisma ORM and helped me easily add seed data - I needed a few prompts to iron out minor issues but all's good. It didn't struggle or got stuck. - Spent $0.50 for this app. Could be way cheaper with the Z.ai sub plans After trying, I can say GLM 4.5 model is up there as the best open source model for coding. Will continue using it and update here. So far so good! P.S. DM me if you want my referral link, otherwise just check Not dropping the link here so it doesn’t look like I’m hyping it. Here's a video of the experience 👇(sped up a bit)

I think I discovered the cheapest way to code with AI 😁 I tried GLM 4.5 on Claude Code and I'm really amazed how good this model is! I usually test with my nextjs crm app benchmark so I asked it to do that. Prompt "create a nextjs app which is a crm app. use sqlite for the database and use api routes to manage connecting to the database from the frontend" My observations - Generation feels like Sonnet 4 intelligence - Speed is great - It used create-next-app so it bootstrapped nextjs v15.5.2 - It created a sqlite database and used Prisma ORM and helped me easily add seed data - I needed a few prompts to iron out minor issues but all's good. It didn't struggle or got stuck. - Spent $0.50 for this app. Could be way cheaper with the Z.ai sub plans After trying, I can say GLM 4.5 model is up there as the best open source model for coding. Will continue using it and update here. So far so good! P.S. DM me if you want my referral link, otherwise just check Not dropping the link here so it doesn’t look like I’m hyping it. Here's a video of the experience 👇(sped up a bit)

Melvin Vivas

45,749 views • 10 months ago

Guessing app's PIN using Flipper Zero as #BadUSB This "App Locker" app protects access to user selected apps - in this case, Instagram - using PIN code. It is possible to guess it with unlimited attempts, because the app developers haven't implemented brute-force protection and even timeout after few incorrect entered passwords. The app only allows to set 4 digit PIN. This allows us to try 10,000 PINs with unlimited attempts. After every try is 0.5 second delay. Because of that, it would take us 84 minutes to rotate through all the PIN combinations. ✅If you decide to use such an app lock protector, make sure not to use easy to guess and common passwords. If you are a developer, I advise you to implement a brute-force protection that includes timeout. #FlipperZero #Android #bruteforce

Guessing app's PIN using Flipper Zero as #BadUSB This "App Locker" app protects access to user selected apps - in this case, Instagram - using PIN code. It is possible to guess it with unlimited attempts, because the app developers haven't implemented brute-force protection and even timeout after few incorrect entered passwords. The app only allows to set 4 digit PIN. This allows us to try 10,000 PINs with unlimited attempts. After every try is 0.5 second delay. Because of that, it would take us 84 minutes to rotate through all the PIN combinations. ✅If you decide to use such an app lock protector, make sure not to use easy to guess and common passwords. If you are a developer, I advise you to implement a brute-force protection that includes timeout. #FlipperZero #Android #bruteforce

Mobile Hacker

220,988 views • 2 years ago

There are very few things that have higher nostalgic value than the memory of The Print Shop (Broderbund, 1984). If you had a dot-matrix printer in the 80s, chances are you used this incredible publishing program. It allowed users to easily create signs, greeting cards, banners, posters, and letterheads using its built-in clip art, fonts, and templates. And if you were the curious type, I’m sure you printed an entire page in black just to see what would happen. In case you never did, let me tell you: it was both a nerve-wracking sound and a totally drenched, soggy piece of paper in the end. (Totally worth it!) Originally launched for the Apple II and later ported to the Commodore 64, IBM PC, and other platforms, it worked with any common dot-matrix printer. Its simple interface meant even 9-year-old me could figure it out. I made covers for virtually anything, from my father's toolbox to my mother's kitchen drawers. It sold over a million copies, and became one of the most popular titles of the era.

There are very few things that have higher nostalgic value than the memory of The Print Shop (Broderbund, 1984). If you had a dot-matrix printer in the 80s, chances are you used this incredible publishing program. It allowed users to easily create signs, greeting cards, banners, posters, and letterheads using its built-in clip art, fonts, and templates. And if you were the curious type, I’m sure you printed an entire page in black just to see what would happen. In case you never did, let me tell you: it was both a nerve-wracking sound and a totally drenched, soggy piece of paper in the end. (Totally worth it!) Originally launched for the Apple II and later ported to the Commodore 64, IBM PC, and other platforms, it worked with any common dot-matrix printer. Its simple interface meant even 9-year-old me could figure it out. I made covers for virtually anything, from my father's toolbox to my mother's kitchen drawers. It sold over a million copies, and became one of the most popular titles of the era.

exQUIZitely 🕹️

33,488 views • 3 months ago

📣 ANNOUNCEMENT 📣 After sweating dozens of shirts, I'm finally proud to announce it. Alohi is available for everyone! 🚀 If you are looking to create tweets out of thin air, this is for you. And here's how ✨ (link to page down below) Alohi is the startup I always wanted to create but didn't have the skills to make it real—or, better yet, the courage. 👉 This March, I learned how to code a SaaS. 👉 In May, 15 people joined the beta. They helped me improve the app, and 5 of them also became customers. 👉 Now, before this quarter ends, my newborn is live! There are so many things to improve. The to-do list feels like a grocery shopping receipt. Alohi doesn't have yet: - a logo - a settings page - nor a proper login page But I don't care. I'm too excited not to share it with you 🤩 So, if you have a newsletter, go check the magic out 👇

Mattia Righetti 👨‍🚀

25,817 views • 2 years ago

Google just shipped a free dictation app for Mac and iPhone called AI Edge Eloquent, and the model running it is Gemma 4 12B, entirely on your device. What it actually does: you speak, it transcribes, removes filler words, and polishes the result before dropping clean text into whatever app you are using. You can also give it voice commands to reformat, like "translate to Hindi" or "make this a bullet list." Audio and video file transcription is built in too. The interesting part is the privacy angle. Most AI writing tools send your audio to a server. This one never leaves your machine, which matters if you are dictating anything sensitive. The tradeoff is hardware: you need a Mac with at least 16GB of RAM to run a 12B parameter model comfortably.

Google just shipped a free dictation app for Mac and iPhone called AI Edge Eloquent, and the model running it is Gemma 4 12B, entirely on your device. What it actually does: you speak, it transcribes, removes filler words, and polishes the result before dropping clean text into whatever app you are using. You can also give it voice commands to reformat, like "translate to Hindi" or "make this a bullet list." Audio and video file transcription is built in too. The interesting part is the privacy angle. Most AI writing tools send your audio to a server. This one never leaves your machine, which matters if you are dictating anything sensitive. The tradeoff is hardware: you need a Mac with at least 16GB of RAM to run a 12B parameter model comfortably.

Aditya ⚡Rao

84,813 views • 1 month ago

$I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)$

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

194,949 views • 11 months ago

Elon Musk: We had to print out 25,000 pages of paper to start Tesla's factory in Germany. Alice Weidel: “We need to free our firms, our companies, and the individuals of these obnoxious bureaucratic conditions here [in Germany]. Do you know how long it takes, how many days it takes to get a business permit in Germany?” Elon Musk: “As it turns out, I do, because we built a gigantic car factory just near Berlin. We had many, many challenges. To be clear, we actually had a lot of support, a lot of local support, a lot of local support from the local government, from the national government. And despite all that support, just the sheer number of rules that the people in the government are required to follow is completely crazy. I think our permit was 25,000 pages, and it had to be all printed on paper. I think maybe more than that in the end. There has to be many, many copies made. It literally was a truck of paper. We were like, surely we can make this electronic? Isn't that better for everyone? And they said, no, it has to be paper. This is crazy. This was only a few years ago. It's not the distant past. We're a quarter of the way through the 21st century. It's like, guys, 25,000 actual printed pages ... I believe every page needed to be stamped with a physical stamp. Honestly, it's going to really tire somebody out to do so much stamping. They're going to get some sort of repetitive stress injury. They will end up in the hospital, I mean, that's too much. But I'm not trying to blame the individuals who are doing this because they are just following the rules. So, we have to change the rules.” Conversation with Alice Weidel, January 9, 2025

Elon Musk: We had to print out 25,000 pages of paper to start Tesla's factory in Germany. Alice Weidel: “We need to free our firms, our companies, and the individuals of these obnoxious bureaucratic conditions here [in Germany]. Do you know how long it takes, how many days it takes to get a business permit in Germany?” Elon Musk: “As it turns out, I do, because we built a gigantic car factory just near Berlin. We had many, many challenges. To be clear, we actually had a lot of support, a lot of local support, a lot of local support from the local government, from the national government. And despite all that support, just the sheer number of rules that the people in the government are required to follow is completely crazy. I think our permit was 25,000 pages, and it had to be all printed on paper. I think maybe more than that in the end. There has to be many, many copies made. It literally was a truck of paper. We were like, surely we can make this electronic? Isn't that better for everyone? And they said, no, it has to be paper. This is crazy. This was only a few years ago. It's not the distant past. We're a quarter of the way through the 21st century. It's like, guys, 25,000 actual printed pages ... I believe every page needed to be stamped with a physical stamp. Honestly, it's going to really tire somebody out to do so much stamping. They're going to get some sort of repetitive stress injury. They will end up in the hospital, I mean, that's too much. But I'm not trying to blame the individuals who are doing this because they are just following the rules. So, we have to change the rules.” Conversation with Alice Weidel, January 9, 2025

ELON CLIPS

5,576,342 views • 1 year ago

#jinxmanhwa my opinion calmly on this: 1. These people who are so extremely critical forget that jinx is a sports story, that it happens in a "realistic" context, jinx is not an omegaverse, nor a story with witchcraft, magic or portals to other universes, if you expected the jinx to be something mystical and magical go read a fantasy story. 2. in my opinion, it is a good justification for the story, jaekyung has always been an obsessive character, many had already deduced that the jinx was going to be related to these "rituals" that athletes use, and it was obvious that it was going to be related to jaekyung's insomnia, since it has been a very important element in the story since the beginning. 3. No, it couldn't have been anyone else besides Kim Dan, if this were the case, he would have continued having sex with anyone after Dan left, Dan has always been the exception for jaekyung. 4. Why am I tweeting about a video from that specific TikTok account? Because I'm sure many of the Jinx haters share that opinion, and it was the first negative video I saw.

#jinxmanhwa my opinion calmly on this: 1. These people who are so extremely critical forget that jinx is a sports story, that it happens in a "realistic" context, jinx is not an omegaverse, nor a story with witchcraft, magic or portals to other universes, if you expected the jinx to be something mystical and magical go read a fantasy story. 2. in my opinion, it is a good justification for the story, jaekyung has always been an obsessive character, many had already deduced that the jinx was going to be related to these "rituals" that athletes use, and it was obvious that it was going to be related to jaekyung's insomnia, since it has been a very important element in the story since the beginning. 3. No, it couldn't have been anyone else besides Kim Dan, if this were the case, he would have continued having sex with anyone after Dan left, Dan has always been the exception for jaekyung. 4. Why am I tweeting about a video from that specific TikTok account? Because I'm sure many of the Jinx haters share that opinion, and it was the first negative video I saw.

Ccyellow

16,869 views • 10 months ago

If ‘MIKE HUCKABEE’ represents what it means to be a “Christian Zionist,” I would HIGHLY suggest that you stop whatever you are doing right now, start pray ing to Jesus Christ our Savior, and beg him to clear your mind from all of this poison... I am starting to see that the majority of you do not truly have a Christian faith. You just use it to benefit in society or for monetary gain. There is NO logic to what Mike Huckabee just shared with the world. It is almost as if they wanted us to see all of the lies that come with it. Even the most indoctrinated of all the fundamentalist Christians can see that there is TOO MUCH wrong with that man's story. I will pray for your soul, but only you can save it‼️

If ‘MIKE HUCKABEE’ represents what it means to be a “Christian Zionist,” I would HIGHLY suggest that you stop whatever you are doing right now, start pray ing to Jesus Christ our Savior, and beg him to clear your mind from all of this poison... I am starting to see that the majority of you do not truly have a Christian faith. You just use it to benefit in society or for monetary gain. There is NO logic to what Mike Huckabee just shared with the world. It is almost as if they wanted us to see all of the lies that come with it. Even the most indoctrinated of all the fundamentalist Christians can see that there is TOO MUCH wrong with that man's story. I will pray for your soul, but only you can save it‼️

Coyote of Wallstreet

16,124 views • 4 months ago

Facebook is such an untapped market for brands These AI animated Facebook accounts generate billions of views every month but barley any brands or apps have capitalised on it fully The thing is every brand / app desperately wants to but they are a shortage of creators to fulfil it The creators who come in and fill this gap for the brands are going to make stupid bread I have a ton of brands reach out to me every week ready to pay creators to make this content So if your a killer AI creator or even just want to be a creator and start making money with content Message under this and I’ll connect you with the brands They’ll each teach you how to make the content so it’s a perfect opportunity

Pounds

20,349 views • 1 month ago

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 views • 4 months ago