Loading video...

Video Failed to Load

Go Home

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...

iannuttall's profile picture

Ian Nuttall

77,436 subscribers

194,803 views • 10 months ago •via X (Twitter)

Science & TechnologyGamingEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

You can just tell Claude Code to learn skills and it will. I asked Claude to create an app that uses tldraw and it one shotted it with sqlite db, and then I asked Claude Code to create a skill so that it could read and write on the canvas. 10 minutes later it could do it. Weirrrrdddd times.
0:25

You can just tell Claude Code to learn skills and it will. I asked Claude to create an app that uses tldraw and it one shotted it with sqlite db, and then I asked Claude Code to create a skill so that it could read and write on the canvas. 10 minutes later it could do it. Weirrrrdddd times.

Riley Brown

73,418 views • 5 months ago

✨ To inspire more people to go build something now that we have AI to help us (especially non-tech people, cause I still know so many who are scared of building something): I added a [ BUILD IT ] button to It's like a mini-Lovable/Replit/v0: Any idea you see you like, you can click [ BUILD IT ], and it will use Opus 4.6 to build a landing page for it And then you can download the code it generated It's not a full startup of course, but a nice preview of what it can be, to give you an idea and inspire you to build it out further The code is live streamed also so you can see it being built 😊 Ironically this itself took me 1 hour to build with AI too Completely free and I pay for the tokens (please don't abuse it :D)
0:55

✨ To inspire more people to go build something now that we have AI to help us (especially non-tech people, cause I still know so many who are scared of building something): I added a [ BUILD IT ] button to It's like a mini-Lovable/Replit/v0: Any idea you see you like, you can click [ BUILD IT ], and it will use Opus 4.6 to build a landing page for it And then you can download the code it generated It's not a full startup of course, but a nice preview of what it can be, to give you an idea and inspire you to build it out further The code is live streamed also so you can see it being built 😊 Ironically this itself took me 1 hour to build with AI too Completely free and I pay for the tokens (please don't abuse it :D)

@levelsio

276,220 views • 2 months ago

After creating Remodex: Codex remote control for iOS I decided to chill a bit by building a browser sidebar inside Theo - t3.gg 's T3 Code You can open it with Cmd+Shift+B This software is so easy to "manipulate" and build upon Congrats to all the guys that put the work in it because it is great I certainly will be building more things with it For this one I decided to switch from the Codex App to the Codex CLI too just to see how it works And boy it was so good
0:20

After creating Remodex: Codex remote control for iOS I decided to chill a bit by building a browser sidebar inside Theo - t3.gg 's T3 Code You can open it with Cmd+Shift+B This software is so easy to "manipulate" and build upon Congrats to all the guys that put the work in it because it is great I certainly will be building more things with it For this one I decided to switch from the Codex App to the Codex CLI too just to see how it works And boy it was so good

Emanuele Di Pietro

38,905 views • 2 months ago

Today, I'm revealing my Roblox Game FULLY scripted using Claude Opus 4.6 Extended. This project took about 4 days to complete, and not a single line of code was touched by an actual scripter. In the conversation I had with Claude, I guided it to complete the entire coding, this game started with a Frontend and a Backend - It is now a fully complete frontpage Roblox Game. From UI Animations, to Visual effect movements, and UI Icons, it was all Claude. The game releases Tomorrow, and I'm expecting it to reach front page on Roblox within a few weeks. 300 Likes, and I'll share the FULL conversation, which was used to build the game. Claude is incredible, this is genuinely an insane movement for coders enhancing their productivity with AI. This is FRICKEN INSANE.
0:52

Today, I'm revealing my Roblox Game FULLY scripted using Claude Opus 4.6 Extended. This project took about 4 days to complete, and not a single line of code was touched by an actual scripter. In the conversation I had with Claude, I guided it to complete the entire coding, this game started with a Frontend and a Backend - It is now a fully complete frontpage Roblox Game. From UI Animations, to Visual effect movements, and UI Icons, it was all Claude. The game releases Tomorrow, and I'm expecting it to reach front page on Roblox within a few weeks. 300 Likes, and I'll share the FULL conversation, which was used to build the game. Claude is incredible, this is genuinely an insane movement for coders enhancing their productivity with AI. This is FRICKEN INSANE.

wst

678,311 views • 3 months ago

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next
1:30

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next

@levelsio

639,785 views • 3 months ago

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):
19:42

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):

Alex Finn

40,858 views • 8 months ago

Clawdbot creator Peter Steinberger 🦞 says Claude Opus is his favorite model, but OpenAI Codex is the best for coding: "OpenAI is very reliable. For coding, I prefer Codex because it can navigate large codebases. You can prompt and have 95% certainty that it actually works. With Claude Code you need more tricks to get the same." "But character wise, [Opus] behaves so good in a Discord it kind of feels like a human. I've only really experienced that with Opus."
1:47

Clawdbot creator Peter Steinberger 🦞 says Claude Opus is his favorite model, but OpenAI Codex is the best for coding: "OpenAI is very reliable. For coding, I prefer Codex because it can navigate large codebases. You can prompt and have 95% certainty that it actually works. With Claude Code you need more tricks to get the same." "But character wise, [Opus] behaves so good in a Discord it kind of feels like a human. I've only really experienced that with Opus."

TBPN

442,352 views • 4 months ago

Okay, I got Claude Code to actually fly my plane now It controls the keys via Chrome by running it with `claude --chrome` There is some issue with the lift vs gravity formula though so it takes a lot of speed to take off, but it's really cool to see it control and fly the plane This means it can code the game and then play it to check in a loop to theoretically improve it without my help (haven't gotten there though) I run it like this btw: `IS_SANDBOX=1 claude --dangerously-skip-permissions --chrome` (Run at your own risk)
3:57

Okay, I got Claude Code to actually fly my plane now It controls the keys via Chrome by running it with `claude --chrome` There is some issue with the lift vs gravity formula though so it takes a lot of speed to take off, but it's really cool to see it control and fly the plane This means it can code the game and then play it to check in a loop to theoretically improve it without my help (haven't gotten there though) I run it like this btw: `IS_SANDBOX=1 claude --dangerously-skip-permissions --chrome` (Run at your own risk)

@levelsio

143,083 views • 4 months ago

Agents can one shot mobile apps, but testing is still the bottleneck. So we built a CLI that gives Claude Code the one thing it was missing - eyes and hands The best part? t's fully vision-based: - No scripts, no selectors, no element IDs - It interacts with the app exactly like a human would Claude now writes code → tests it on the app → sees what broke → fixes it Spawn a cloud agent, go to sleep, and wake up knowing it actually worked.
0:38

Agents can one shot mobile apps, but testing is still the bottleneck. So we built a CLI that gives Claude Code the one thing it was missing - eyes and hands The best part? t's fully vision-based: - No scripts, no selectors, no element IDs - It interacts with the app exactly like a human would Claude now writes code → tests it on the app → sees what broke → fixes it Spawn a cloud agent, go to sleep, and wake up knowing it actually worked.

Landseer Enga

86,799 views • 3 months ago

When using GPT-5.5, it is instantly noticeable how much more powerful it is. In Codex, I gave it a very complex prompt to create London Toy Railway with landmarks and seasons - it did an excellent job in one shot. In the second half of the video you see GPT-5.4 - it was also not bad, but very clearly worse. GPT-5.5's generation is far more ambitious, coherent and with fewer errors. This is obviously a toy example, but I've used it on much more complex real tasks, including a complex app migration and a new hard workflow - it has been working away for many hours without getting stumped. I'm getting more and more addicted to this stuff with every model release.
0:49

When using GPT-5.5, it is instantly noticeable how much more powerful it is. In Codex, I gave it a very complex prompt to create London Toy Railway with landmarks and seasons - it did an excellent job in one shot. In the second half of the video you see GPT-5.4 - it was also not bad, but very clearly worse. GPT-5.5's generation is far more ambitious, coherent and with fewer errors. This is obviously a toy example, but I've used it on much more complex real tasks, including a complex app migration and a new hard workflow - it has been working away for many hours without getting stumped. I'm getting more and more addicted to this stuff with every model release.

Peter Gostev

261,358 views • 1 month ago

soon you're going to be able to have AI autonomously build apps for you, with no human in the loop. me, someone who can't code, can make an app with - Claude Computer Agent, that controls Cursor - clones a github repo - opens composer in agent mode - and prompts it with an app idea - and then waits for the Cursor Agent to finish Then I prompted that agent to test the app! (template @senior_swc)
1:34

soon you're going to be able to have AI autonomously build apps for you, with no human in the loop. me, someone who can't code, can make an app with - Claude Computer Agent, that controls Cursor - clones a github repo - opens composer in agent mode - and prompts it with an app idea - and then waits for the Cursor Agent to finish Then I prompted that agent to test the app! (template @senior_swc)

Riley Brown

48,960 views • 1 year 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)
0:38

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 • 9 months ago

✨ Added a CRT curvature distortion to pieter™ now It takes the Em-DOSBox and processes it in WebGL and builds a new with the distortion of a classic CRT screen which had this convex curvature (like an old TV) even though the screen itself was square I had this working on DOSBox on MacOS and on Linux with CRT-Pi shader, but on web it doesn't support shaders so I had to build my own with Claude Code in JS, very easy I remember trying this a year ago and Claude Code fucked it up so bad that I gave up, so I think the models have improved a lot Tomorrow I'll try add some scanlines, it really helps make the simulation more passable (and nostalgic!) 😊👌
2:20

✨ Added a CRT curvature distortion to pieter™ now It takes the Em-DOSBox and processes it in WebGL and builds a new with the distortion of a classic CRT screen which had this convex curvature (like an old TV) even though the screen itself was square I had this working on DOSBox on MacOS and on Linux with CRT-Pi shader, but on web it doesn't support shaders so I had to build my own with Claude Code in JS, very easy I remember trying this a year ago and Claude Code fucked it up so bad that I gave up, so I think the models have improved a lot Tomorrow I'll try add some scanlines, it really helps make the simulation more passable (and nostalgic!) 😊👌

@levelsio

87,993 views • 4 months ago

Sam Altman on GPT 5: "This morning I was testing our new model and I got a question. I got emailed a question that I didn't quite understand. And I put it in the model, this is GPT-5, and it answered it perfectly. And I really kind of sat back in my chair and I was just like, oh man, here it is moment... I felt like useless relative to the AI in this thing that I felt like I should have been able to do and I couldn't. It was really hard. But the AI just did it like that. It was a weird feeling."
0:46

Sam Altman on GPT 5: "This morning I was testing our new model and I got a question. I got emailed a question that I didn't quite understand. And I put it in the model, this is GPT-5, and it answered it perfectly. And I really kind of sat back in my chair and I was just like, oh man, here it is moment... I felt like useless relative to the AI in this thing that I felt like I should have been able to do and I couldn't. It was really hard. But the AI just did it like that. It was a weird feeling."

Chris

5,663,128 views • 10 months ago

The moment that drew my attention to Freen was when you went to Cannes and there was a photo of your in a red dress which got tenth of thousands of likes—I was like, who’s this? I want to ask how you view Cannes before and after you went there. When I found out that I will be there, I felt it was such a grand event. Never imagined… like me? ME? Who am I to get to go there? And when I was there… it was really grand. And the photo time was so long that I thought…. Are we done? Didn’t know what to pose already. Was very nervous inside but had to act confident. Come…. Take photos… but inside, scan around…. How many? How long is the camera wall😅 It’s a good moment in life. Saw Queen Chompoo went so many years and looked so grand every time. I was one who was excited to see what she will wear. So when it was me, I was excited. And when was there, was a bit pressured—what dress and accessories to wear. I had to do a lot of homework. I was a bit surprised with myself. They have dresses for me to choose from. Had to pick what fitted me. But when I liked the red design… but it was red, which I have to wear to a red carpet… I was like… what to do… and decided to go for it. I’ll go with it. Not sure how red on red will be but went with it. MC: for me it was a good choice. I felt. This kid is brave. You could handle it and made it seem effortless/ not stressed. Felt you weren’t stressed out by the red carpet. I thought you handled it well. Thank you so much. It was my first time. I was really scared. The necklace. I’ll tell you about was the first time in my life that I went to choose it all by myself. Had to pick accessories worth many tenth of millions alone. Had to go through 3-4 doors with massive guards and there was one guard with me. They went do you like this, no? Next. No? Next. Was not able to put on the dress and tried… had to imagined it. I think that room had accessories worth tenths of billions. All could do was put it against my neck and imagined it with the dress I picked. Was difficult but I think I got a perfect total look. MC: I’m also interested to know which part you like the most about Cannes aside from the red carpet. There were so many eventful stuff. First I missed my flight! Instead of two stops/transfer I had to take four or five. …. …. Anyway that’s fine. My team was good and professional—the manager, makeup, hair. We had to deal with the situation but got through it while still had good humor about it. MC: what thought about hotel Martinez iconic stairs. Met so many people/celebrities. It was like a check in spot for everyone. After you finished getting ready, had to take photos there. It was another memorable moment. Not everyone can be there. Overall, glad I experienced getting ready there and went to the red carpet.
5:41

The moment that drew my attention to Freen was when you went to Cannes and there was a photo of your in a red dress which got tenth of thousands of likes—I was like, who’s this? I want to ask how you view Cannes before and after you went there. When I found out that I will be there, I felt it was such a grand event. Never imagined… like me? ME? Who am I to get to go there? And when I was there… it was really grand. And the photo time was so long that I thought…. Are we done? Didn’t know what to pose already. Was very nervous inside but had to act confident. Come…. Take photos… but inside, scan around…. How many? How long is the camera wall😅 It’s a good moment in life. Saw Queen Chompoo went so many years and looked so grand every time. I was one who was excited to see what she will wear. So when it was me, I was excited. And when was there, was a bit pressured—what dress and accessories to wear. I had to do a lot of homework. I was a bit surprised with myself. They have dresses for me to choose from. Had to pick what fitted me. But when I liked the red design… but it was red, which I have to wear to a red carpet… I was like… what to do… and decided to go for it. I’ll go with it. Not sure how red on red will be but went with it. MC: for me it was a good choice. I felt. This kid is brave. You could handle it and made it seem effortless/ not stressed. Felt you weren’t stressed out by the red carpet. I thought you handled it well. Thank you so much. It was my first time. I was really scared. The necklace. I’ll tell you about was the first time in my life that I went to choose it all by myself. Had to pick accessories worth many tenth of millions alone. Had to go through 3-4 doors with massive guards and there was one guard with me. They went do you like this, no? Next. No? Next. Was not able to put on the dress and tried… had to imagined it. I think that room had accessories worth tenths of billions. All could do was put it against my neck and imagined it with the dress I picked. Was difficult but I think I got a perfect total look. MC: I’m also interested to know which part you like the most about Cannes aside from the red carpet. There were so many eventful stuff. First I missed my flight! Instead of two stops/transfer I had to take four or five. …. …. Anyway that’s fine. My team was good and professional—the manager, makeup, hair. We had to deal with the situation but got through it while still had good humor about it. MC: what thought about hotel Martinez iconic stairs. Met so many people/celebrities. It was like a check in spot for everyone. After you finished getting ready, had to take photos there. It was another memorable moment. Not everyone can be there. Overall, glad I experienced getting ready there and went to the red carpet.

panpan

25,405 views • 2 months ago

I built a form-filling agent that anyone can use 💫 This is an extremely simple but useful (I hope) app. Upload a fillable form 📋, some context files, and chat with the agent to fill the form out automatically ✍️ 1️⃣ Yes it is a Claude Code SDK wrapper 2️⃣ It is better and faster than ChatGPT/Claude UI out of the box 3️⃣ We use LlamaParse to parse the context files, so you can have more trust that we are able to read context without hallucinations (e.g. messy scanned handwriting, drivers license photo, and more). This was one of my holiday Claude Code vibe-coding projects. Built with Opus 4.5, and also powered by Opus 4.5. Feeling the AGI 🫡 App is here: Repo is open-source:
1:48

I built a form-filling agent that anyone can use 💫 This is an extremely simple but useful (I hope) app. Upload a fillable form 📋, some context files, and chat with the agent to fill the form out automatically ✍️ 1️⃣ Yes it is a Claude Code SDK wrapper 2️⃣ It is better and faster than ChatGPT/Claude UI out of the box 3️⃣ We use LlamaParse to parse the context files, so you can have more trust that we are able to read context without hallucinations (e.g. messy scanned handwriting, drivers license photo, and more). This was one of my holiday Claude Code vibe-coding projects. Built with Opus 4.5, and also powered by Opus 4.5. Feeling the AGI 🫡 App is here: Repo is open-source:

Jerry Liu

48,342 views • 4 months ago

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base
1:47

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Malte Ubl

124,713 views • 5 months ago

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!
0:42

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

255,761 views • 1 year ago

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."
2:54

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

The Pragmatic Engineer

62,476 views • 1 month ago

haha, i used OpenAI operator build, deploy, and open source a tool on github using Replit ⠕ agent. took about 30 min, here's an ~8 min supercut video thoughts: - while working with replit agent, it actually deployed the app, tested it, and described the error back to replit agent for me - operator asked me a few more Qs than i wanted, but it was mostly for safety (eg filling forms) so i guess okay with it - it had trouble with a few things around UI like knowing it needs to scroll a page to see the rest of it, and it needed pointers to find the git feature in replit - once it found the git feature it didn't need my assistance to create a repo and open source after having the agent write a readme while a bit slower, this was even more automated than replit agent (especially testing features and working through errors) - which is impressive would be nice to have: push notifications for when it needs my attention, and voice mode capabilities
7:50

haha, i used OpenAI operator build, deploy, and open source a tool on github using Replit ⠕ agent. took about 30 min, here's an ~8 min supercut video thoughts: - while working with replit agent, it actually deployed the app, tested it, and described the error back to replit agent for me - operator asked me a few more Qs than i wanted, but it was mostly for safety (eg filling forms) so i guess okay with it - it had trouble with a few things around UI like knowing it needs to scroll a page to see the rest of it, and it needed pointers to find the git feature in replit - once it found the git feature it didn't need my assistance to create a repo and open source after having the agent write a readme while a bit slower, this was even more automated than replit agent (especially testing features and working through errors) - which is impressive would be nice to have: push notifications for when it needs my attention, and voice mode capabilities

Yohei

211,778 views • 1 year ago