Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

I failed to make a web app on both Replit & Lovable (and I code). I still think every PM should try this at least once. Bottom line: • I didn't need to "code," but at some point I was definitely doing engineering. • Building a complex web application... takes babysitting • These tools are amazing for expressing ideas and visualizing data • PMs, try this out! It builds intuition for being on the other side of an agent (and now you don't have to be afraid of failing) My background: I can build web apps (though I became a PM because I was pretty bad at it) What I wanted to build: I wanted to replicate Graphtreon (unofficial patreon scraper and public revenue dashboard), but for Maven (where my course is hosted). How it went for me: 🟢 ChatGPT/Claude helped me iterate to a great prompt (literally, "help me write a prompt for an AI LLM prototyping tool to build a web app that...") 🟢 I pasted that into both Lovable and Replit (why not open two tabs) 🟢 Iterating on the UI was awesome. If I kept feedback high-level, it would think of all the little flow details on its own (confirmation dialogs, errors) 🟡 It had backend powers, but needed a lot of obvious help on setting up simple backend web scraping (not nobel prize type work) 🟡 I tried to "empower" it with higher-level goals, but kept getting dragged back down to troubleshooting 🔴 I found myself babysitting every error, and building features solely for the purpose of observability and debugging 🔴 I was having fun, but for the wrong reasons (breaking through frustrating walls rather than for outcomes, insights, or innovation) That said, my friend succeeded. A former PM colleague (now founder) successfully built a web app using Lovable, and reported the same experience. He succeeded because he was way more persistent (spent many days fully focused on this) and also smarter. These tools are in a weird, adolescent neither-here-nor-there stage. That said, I'm still super impressed, and can't believe this even exists. Most importantly for product managers: I recommend trying this hands-on ✓ Timebox yourself to an hour ✓ What's a piece of software you didn't get approval to buy? ✓ Allow yourself to get in the weeds, if only as an exercise ✓ Build intuition for what it's like to be on the other side of an agent doing something really complex. Now you don't have to feel bad if you fail :)show more

Tal Raviv

3,941 subscribers

41,306 просмотров • 1 год назад •via X (Twitter)

Наука и технологии Образование

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля Kabir Khorwal

Kabir Khorwal1 год назад

Try using Far more intuitive & feature-rich as compared to replit & lovable.

Фото профиля Steve Mallett 🇨🇦

Steve Mallett 🇨🇦1 год назад

I'm a PM who has shipped my first app completely without writing any code myself using AI tools. You're gonna need to get your hands dirty and hit some brick walls.... just like learning anything.

Фото профиля Batsirai

Batsirai1 год назад

Today is the worst it will ever be. I’m a PM, and I love it… but yes it takes time and patience and can be really frustrating. HOWEVER. we must remember we are going exponentially faster than we ever could. When you are on a long flight… it seems slow and mind numbingly painful (Are we there yet?? - clicking to see the flight map) - buy while it feels that way, we are actually going faster than anyone in the history of humanity. Taking hours for what one took months. This is LLM development or vibe coding. It’s slow… but fast. (For those who couldn’t code themselves)

Фото профиля MrLogistics

MrLogistics2 лет назад

I talk a big game about saving ecom clients on shipping rates. Well, I've saved: • $50M between clients in 2 years • @luxurywatchguy $200k in 4 hours • Dozens of clients 10-50% (for a decade now!) Want to learn how? Follow me @MisterLogistic

Фото профиля MS

MS1 год назад

Hi Tal, Great content! Perhaps give pretty sure you'll find the experience more tailored for your needs. Give us a try Ahi 😉

Фото профиля Ethan Torbenson

Ethan Torbenson1 год назад

@fredherrera You can really just do things. You just need persistence and a little bit of savvy and you can figure it out.

Фото профиля Aman Mathur

Aman Mathur1 год назад

great summary - if you have any replit specific requests or feedback DMs are open :)

Фото профиля Aaron Chiandet

Aaron Chiandet1 год назад

Easily the most sound and measured take on the topic. I also had the exact same experience trying to be completely hands off but it always devolved into painful debugging cycles that it couldn’t get itself out of. One day we will be there. Today is not that day.

Фото профиля Ari Akerstein

Ari Akerstein1 год назад

Replit is incredible. I think I’m willing to suffer through unreasonable amounts…so much nicer prompting vs debugging with no support. Every time I keep thinking - whatever this agent produces in 30 sec would have taken me 15m at least

Фото профиля Alex Bi

Alex Bi1 год назад

I've found windsurf w/ sonnet much better at handling backend tasks. v0/lovable/bolt are great as a starting point for the UI screens. Overall experience is v relatable from my experience. To build anything meaningful still requires a solid amount of debugging

Фото профиля Ishwar Jha

Ishwar Jha1 год назад

I absolutely subscribe to your thoughts and ideas.

Похожие видео

BREAKING: Replit just launched mobile apps. Now you can build in Replit ⠕ and submit straight to the App Store for review. Describe your app → build it on Replit → test on your phone → publish to the App Store. I built a unicorn pet app for my niece: - Worked with Replit Agent to build it out - Scanned a QR code to download and test on my phone - One click to send to App Store Connect for review - A couple submissions later, it's live in the App Store! 🙌 I didn't write a single line of code! Just described what I wanted to Agent. Amazing! 😅 Go build something!! 👇

BREAKING: Replit just launched mobile apps. Now you can build in Replit ⠕ and submit straight to the App Store for review. Describe your app → build it on Replit → test on your phone → publish to the App Store. I built a unicorn pet app for my niece: - Worked with Replit Agent to build it out - Scanned a QR code to download and test on my phone - One click to send to App Store Connect for review - A couple submissions later, it's live in the App Store! 🙌 I didn't write a single line of code! Just described what I wanted to Agent. Amazing! 😅 Go build something!! 👇

Manny Bernabe

30,925 просмотров • 4 месяцев назад

I just shipped Design Feedback Agent using Replit ⠕ agent without writing a single line of code. You can use this agent to get constructive feedback on your designs--website, mobile app, email newsletter etc. Check out the video demo, and try it for yourself at My biggest takeaway as I continue to experiment with these tools is how good they are getting at building complex flows and how precise they are at taking design feedback and applying it accurately from a text prompt. I'm excited to build even more complex products to see how far I can push these tools. Let me know what you think of this agent and how you would improve it.

I just shipped Design Feedback Agent using Replit ⠕ agent without writing a single line of code. You can use this agent to get constructive feedback on your designs--website, mobile app, email newsletter etc. Check out the video demo, and try it for yourself at My biggest takeaway as I continue to experiment with these tools is how good they are getting at building complex flows and how precise they are at taking design feedback and applying it accurately from a text prompt. I'm excited to build even more complex products to see how far I can push these tools. Let me know what you think of this agent and how you would improve it.

Levin Stanley

17,762 просмотров • 1 год назад

We live in the solo founder era. That's for sure and building with AI has accelerated. I am building software to use for myself and replace the expensive tools I used to use. And partially thanks to AI we can build faster, but not dramatically faster if you want to build a commercial grade product. Before I was using a live chat and customer support tool that costed around 50-100$ a month. This helped me to interact with the customers of my agency or prospects. But I decided a few months ago to build my own and stop paying for these more expensive solutions. I did and turned into a product for everyone to use. The build was not 1-2 hours of work using AI, but it was a several-month process on and off as I needed it. Finally, it has turned into a commercial grade product. I have built several of these and this is when we will see more and more solutions like these. Let's start bootstrapping before showing MRR figures.

We live in the solo founder era. That's for sure and building with AI has accelerated. I am building software to use for myself and replace the expensive tools I used to use. And partially thanks to AI we can build faster, but not dramatically faster if you want to build a commercial grade product. Before I was using a live chat and customer support tool that costed around 50-100$ a month. This helped me to interact with the customers of my agency or prospects. But I decided a few months ago to build my own and stop paying for these more expensive solutions. I did and turned into a product for everyone to use. The build was not 1-2 hours of work using AI, but it was a several-month process on and off as I needed it. Finally, it has turned into a commercial grade product. I have built several of these and this is when we will see more and more solutions like these. Let's start bootstrapping before showing MRR figures.

andrei saioc

14,422 просмотров • 1 год назад

Jelly Hoshiumi has made a short statement at the beginning of her stream. "So I just want to take this moment to, um, say that... Okay, it's really no big deal but I am sorry to-to my friends and my company for making it- I wrote this all on my own by the way- for, you know, making it kind of, you know, suck on twitter. com. (...) I-I'm sorry for inconveniencing you and stressing you out most importantly. (...) I feel kind of bad for, you know, stressing you out with everything and also not streaming and I feel bad for that. That is what I feel bad for. Also just to clarify, I'm not a racist, I'm not a bigot. And most importantly I would like to thank you for the support" "I feel like I have to elaborate a bit because I was a bit nervous when I was making the statement (...) Right, so I feel like now that everything's calmed down a little bit, I feel like I can kind of say that, everything is actually cool between me and the company. (...) Sakana did personally send me an apology, so we're actually pretty good. We've been talking, I sent- I took a picture of a book and I sent it to him, I asked if he wanted it. He said yeah. So everything is actually fine, So don't worry about it, okay? It's good. I don't want you guys to be angry, I don't want you guys to be upset on behalf of me if anything, I just want you guys to be chill. Just like me and just let it go."

Sensitive content

Jelly Hoshiumi has made a short statement at the beginning of her stream. "So I just want to take this moment to, um, say that... Okay, it's really no big deal but I am sorry to-to my friends and my company for making it- I wrote this all on my own by the way- for, you know, making it kind of, you know, suck on twitter. com. (...) I-I'm sorry for inconveniencing you and stressing you out most importantly. (...) I feel kind of bad for, you know, stressing you out with everything and also not streaming and I feel bad for that. That is what I feel bad for. Also just to clarify, I'm not a racist, I'm not a bigot. And most importantly I would like to thank you for the support" "I feel like I have to elaborate a bit because I was a bit nervous when I was making the statement (...) Right, so I feel like now that everything's calmed down a little bit, I feel like I can kind of say that, everything is actually cool between me and the company. (...) Sakana did personally send me an apology, so we're actually pretty good. We've been talking, I sent- I took a picture of a book and I sent it to him, I asked if he wanted it. He said yeah. So everything is actually fine, So don't worry about it, okay? It's good. I don't want you guys to be angry, I don't want you guys to be upset on behalf of me if anything, I just want you guys to be chill. Just like me and just let it go."

Rima Evenstar

42,650 просмотров • 3 месяцев назад

This part breaks and heals my heart at the same time 💔Mingi’s words are full of wisdom, as always🥺 🐥 I was full of arrogance in the beginning, but after I made my debut, I felt so small. From then on, I lost a lot of my mental strength. As soon as I made my debut, I thought I was the best and I thought I was in first place. That’s why those aspirations, that tenacity, and that something about me - my self-worth - was so high. But after that, it was destroyed in an instant. 🐥 I lost a lot of my self-worth, and I started to feel like I was worth nothing. I started to doubt if there was any reason for me to be in this group. When I feel that kind of self-disgust, I think it’s important how I overcome those thoughts. In my early days of my debut, I think I only had a pretty packaging on me. I used to think, ‘I’m doing well, what more can I do?’ But after that pretty packaging came off, I had nothing inside. So I think it took me a long time to fill myself up. Now, even if I break down once in a while, I just go back to the human Song Mingi, and I look for the things I like one by one, and then I think, ‘People will like me a bit now, right?’ Since we’re celebrities, we need to satisfy the people to a certain degree. But I think we still have to satisfy ourselves in the process as well. I think I try to find a harmony between the two in my head. 🐥 It took me a long time to build this up, but I think the process of building myself up, unlike building a sand castle, you build it up little by little. So I feel like, internally, I have become more resilient, compare to before.

This part breaks and heals my heart at the same time 💔Mingi’s words are full of wisdom, as always🥺 🐥 I was full of arrogance in the beginning, but after I made my debut, I felt so small. From then on, I lost a lot of my mental strength. As soon as I made my debut, I thought I was the best and I thought I was in first place. That’s why those aspirations, that tenacity, and that something about me - my self-worth - was so high. But after that, it was destroyed in an instant. 🐥 I lost a lot of my self-worth, and I started to feel like I was worth nothing. I started to doubt if there was any reason for me to be in this group. When I feel that kind of self-disgust, I think it’s important how I overcome those thoughts. In my early days of my debut, I think I only had a pretty packaging on me. I used to think, ‘I’m doing well, what more can I do?’ But after that pretty packaging came off, I had nothing inside. So I think it took me a long time to fill myself up. Now, even if I break down once in a while, I just go back to the human Song Mingi, and I look for the things I like one by one, and then I think, ‘People will like me a bit now, right?’ Since we’re celebrities, we need to satisfy the people to a certain degree. But I think we still have to satisfy ourselves in the process as well. I think I try to find a harmony between the two in my head. 🐥 It took me a long time to build this up, but I think the process of building myself up, unlike building a sand castle, you build it up little by little. So I feel like, internally, I have become more resilient, compare to before.

Irene | AhgaTiny

35,998 просмотров • 9 месяцев назад

tired: Claude Code ports my personal website to a new framework wired: Claude Code generates a command center UI where I can execute the port! with live feedback, including a side-by-side preview of old / new site 😎 this is an example of what I call an "AI HUD" -- a "heads-up display" that gives me visibility into what's going on. i can see: - what terminal commands are running - what files are being created on disk - a live running preview of the old / new website (!) this HUD was actually my third attempt at doing this task, and I liked it the best. here's why I landed there: I wanted to move from middleman to astro for my personal site. These are both static site generators that output html, so I suspected an AI agent could do a good job with a port -- since it could compare old / new build output and try to match. Attempt 1: Agent I just had Claude Code do the port. It went pretty well. But it was hard for me to review what had happened! The git diff was dozens of new files and it was hard to tell how they mapped to the old site. I think the LLM also tried directly writing some files rather than doing deterministic copying, which felt dangerous. Attempt 2: Script I realized a better approach was to have Claude Code write a script that would do the port. The script would execute shell commands like "copy all the markdown files from this directory into this other directory in the new site". This worked much better because I could review the *process* rather than the *results*. Still, even with a nicely commented script, it felt like I was doing a lot of work to review. I wondered: how could I make it ridiculously easy to review this? Attempt 3: HUD Enter the command center! This is an entire web app that I had Claude build just for this one task. I can click buttons to run each step of the port, and watch the new website gradually materialize. It has a node server that runs on my local machine that executes commands on my filesystem and coordinates dev servers for the old/new site. And then a web UI that talks to that server to visualize terminal commands, file trees, and live running previews. It's a HUD because I feel like I can ambiently see everything that the port process is doing 🧐 Was this whole thing worth making for this one-time task? I'm not sure, maybe it was overkill 😅 But it did help me feel more confident that I understood what was going on, and total time was still less than it would have taken me to do the whole port by hand! One way to look at this experience is: "AI can put absurd amounts of effort into a pull request description." What do I mean by that? Well, a PR description is a way to communicate a code change to a human. Typically we do that by writing a bit of text, because that's all we have time for. But given more time and effort, we can do better! An interactive command center / HUD can help a person understand what a code change is actually doing. Historically you'd never imagine investing the effort to do that for a single PR. But now it's within the realm of possibility. So, next time you have an agent do something for you, and you wish you understood better what it was doing, consider: instead of just asking for textual descriptions, maybe ask the agent to make you a HUD!

tired: Claude Code ports my personal website to a new framework wired: Claude Code generates a command center UI where I can execute the port! with live feedback, including a side-by-side preview of old / new site 😎 this is an example of what I call an "AI HUD" -- a "heads-up display" that gives me visibility into what's going on. i can see: - what terminal commands are running - what files are being created on disk - a live running preview of the old / new website (!) this HUD was actually my third attempt at doing this task, and I liked it the best. here's why I landed there: I wanted to move from middleman to astro for my personal site. These are both static site generators that output html, so I suspected an AI agent could do a good job with a port -- since it could compare old / new build output and try to match. Attempt 1: Agent I just had Claude Code do the port. It went pretty well. But it was hard for me to review what had happened! The git diff was dozens of new files and it was hard to tell how they mapped to the old site. I think the LLM also tried directly writing some files rather than doing deterministic copying, which felt dangerous. Attempt 2: Script I realized a better approach was to have Claude Code write a script that would do the port. The script would execute shell commands like "copy all the markdown files from this directory into this other directory in the new site". This worked much better because I could review the process rather than the results. Still, even with a nicely commented script, it felt like I was doing a lot of work to review. I wondered: how could I make it ridiculously easy to review this? Attempt 3: HUD Enter the command center! This is an entire web app that I had Claude build just for this one task. I can click buttons to run each step of the port, and watch the new website gradually materialize. It has a node server that runs on my local machine that executes commands on my filesystem and coordinates dev servers for the old/new site. And then a web UI that talks to that server to visualize terminal commands, file trees, and live running previews. It's a HUD because I feel like I can ambiently see everything that the port process is doing 🧐 Was this whole thing worth making for this one-time task? I'm not sure, maybe it was overkill 😅 But it did help me feel more confident that I understood what was going on, and total time was still less than it would have taken me to do the whole port by hand! One way to look at this experience is: "AI can put absurd amounts of effort into a pull request description." What do I mean by that? Well, a PR description is a way to communicate a code change to a human. Typically we do that by writing a bit of text, because that's all we have time for. But given more time and effort, we can do better! An interactive command center / HUD can help a person understand what a code change is actually doing. Historically you'd never imagine investing the effort to do that for a single PR. But now it's within the realm of possibility. So, next time you have an agent do something for you, and you wish you understood better what it was doing, consider: instead of just asking for textual descriptions, maybe ask the agent to make you a HUD!

Geoffrey Litt

62,839 просмотров • 9 месяцев назад

Raven was asked when he was in ECW, was the goal to get back to WWE or WCW? “I was really happy at ECW but yes, I wanted to go back to WWE. I wanted to be the top guy in the top promotion. I got to be the top guy in the number three promotion. And for a long time, I felt like my career was a failure because of that. I think I talked about it in the movie, in the documentary, but it took a lot of time on a therapist couch to let myself off the hook. Because you hold yourself to such a high standard that I can’t see the forest for the trees. If anybody would have came up to me and told me what my career was, and it was theirs. I said, Man, you got a really successful career. But I couldn’t count it as with that for me, because I didn’t get to be a World Champion of the WWE. (Chris Van Vliet)

Raven was asked when he was in ECW, was the goal to get back to WWE or WCW? “I was really happy at ECW but yes, I wanted to go back to WWE. I wanted to be the top guy in the top promotion. I got to be the top guy in the number three promotion. And for a long time, I felt like my career was a failure because of that. I think I talked about it in the movie, in the documentary, but it took a lot of time on a therapist couch to let myself off the hook. Because you hold yourself to such a high standard that I can’t see the forest for the trees. If anybody would have came up to me and told me what my career was, and it was theirs. I said, Man, you got a really successful career. But I couldn’t count it as with that for me, because I didn’t get to be a World Champion of the WWE. (Chris Van Vliet)

J O H N

26,404 просмотров • 5 месяцев назад

(long clip & transcription ‼️) 🎭: if i was asked one year ago if i wanted to perform in Concerto, i would've said no. there was a different kind of event that i was asked if i would like to participate and i actually said no to it. because up until recently like a few months ago, i had extremely bad imposter syndrome. 🎭: i didn't feel like i deserved to stand on stage, i didn't feel like i was ready and i kept doubting myself and was like "there's no way i would be able to perform to people's standards and stuff" so i politely declined being in an event a long time ago. 🎭: this time for Concerto when i was asked to participate, i was thinking of the same thing too but i thought about it a little more. i thought to myself like "if you're not gonna participate now then when are you going to do it? if you keep saying no to all these opportunities, they're all going to slip past." so i keep telling myself, "if you're gonna do it now then when are you going to do it?" 🎭: and i was inspired a little by my recent short covers and dance covers because ive been planning to release them for quite a long time actually. just the thought of that made me think, "i'm trying to work so hard on these other things so why don't i just try to do this as well?" 🎭: so i finally decided that i'm going to try this time to step up on stage and i want to be the proof to everyone that works hard that if you work hard eventually something good will come your way 🎭: i want everyone to be able to look at me and be like, "if he can work hard and do what he wants to do, then i can do it too." i think that's one of the biggest reasons i decided to participate and stand on this stage is because i want to inspire people because i came from nothing 🎭: i had no singing experience, no dancing experience, no japanese experience. when i first joined, i didn't even know how to read hiragana very well. i didn't even know wtf katakana was 🎭: i'm always thankful for the love and support everyone gives me. if it wasn't for you guys, i would really have said no so thank you. i really owe everything to all of you that always around and always supporting #knoxclips thank you for not giving up!!!! 😭🧡

(long clip & transcription ‼️) 🎭: if i was asked one year ago if i wanted to perform in Concerto, i would've said no. there was a different kind of event that i was asked if i would like to participate and i actually said no to it. because up until recently like a few months ago, i had extremely bad imposter syndrome. 🎭: i didn't feel like i deserved to stand on stage, i didn't feel like i was ready and i kept doubting myself and was like "there's no way i would be able to perform to people's standards and stuff" so i politely declined being in an event a long time ago. 🎭: this time for Concerto when i was asked to participate, i was thinking of the same thing too but i thought about it a little more. i thought to myself like "if you're not gonna participate now then when are you going to do it? if you keep saying no to all these opportunities, they're all going to slip past." so i keep telling myself, "if you're gonna do it now then when are you going to do it?" 🎭: and i was inspired a little by my recent short covers and dance covers because ive been planning to release them for quite a long time actually. just the thought of that made me think, "i'm trying to work so hard on these other things so why don't i just try to do this as well?" 🎭: so i finally decided that i'm going to try this time to step up on stage and i want to be the proof to everyone that works hard that if you work hard eventually something good will come your way 🎭: i want everyone to be able to look at me and be like, "if he can work hard and do what he wants to do, then i can do it too." i think that's one of the biggest reasons i decided to participate and stand on this stage is because i want to inspire people because i came from nothing 🎭: i had no singing experience, no dancing experience, no japanese experience. when i first joined, i didn't even know how to read hiragana very well. i didn't even know wtf katakana was 🎭: i'm always thankful for the love and support everyone gives me. if it wasn't for you guys, i would really have said no so thank you. i really owe everything to all of you that always around and always supporting #knoxclips thank you for not giving up!!!! 😭🧡

luna 🧸

33,769 просмотров • 6 месяцев назад

✨ 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)

✨ 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

276,281 просмотров • 2 месяцев назад

Ok, my mind is blown with Replit Agents. I started using it because I was bored on a train ride a couple of days ago. So today I tried to build a Trello clone and build a fully functional app in like 45 mins. I showed it to a few people in the office and the guy is like "I should quit my job." He built a stock tracking app in 2 mins and added a few features he wanted. I can't imagine the world being the same in 10 years if software writing could be supercharged like this. Replit has really hit it out of the park. I don't need ChatGPT now. I'll just build apps in Replit. I'm a fan and a convert.

Ok, my mind is blown with Replit Agents. I started using it because I was bored on a train ride a couple of days ago. So today I tried to build a Trello clone and build a fully functional app in like 45 mins. I showed it to a few people in the office and the guy is like "I should quit my job." He built a stock tracking app in 2 mins and added a few features he wanted. I can't imagine the world being the same in 10 years if software writing could be supercharged like this. Replit has really hit it out of the park. I don't need ChatGPT now. I'll just build apps in Replit. I'm a fan and a convert.

Rohit Mittal

205,257 просмотров • 1 год назад

This might be the best "AI Engineer" I've tried so far. I'm an old school developer who started 30 years ago. I feel very uncomfortable letting AI take control of my code, but for the sake of science, I spent two hours building an application that took me weeks to build a couple of years ago. I used Pythagora, a brand new tool backed by Y Combinator. They just released to the public. Keep in mind that I use AI every day to write code, but Pythagora is something different: it's a tool that leads, and uses you—the human—as the copilot. I go into more details in the video, but here is the TLDR; 1. Holy molly! We've made a ton of progress on this front! This is way better than Devin when I tested it a few months back. 2. Love the approach of generating a plan with sub-tasks before writing any code. 3. The tools never tries to do too much: it tackles every small task one at a time, and gives you instructions so you test everything. 4. It does exactly what you'd do when it gets stuck: writes a bunch of logs and uses those to correct itself. Pretty neat! 5. It's fast. It runs locally. It's an extension to Visual Studio Code. I'm impressed, but I don't think this tool is for me. I'm not the type of developer who's ready to relinquish control. I felt I had no connection with the code because I didn't write it. It was not my code. I know many people who don't care about this. I know many people who will get tremendous value out of Pythagora. I hope they keep pushing the limits, providing feedback, and helping this get to a point where old folks like me feel more comfortable using it. Don't take my word for it. The best thing you can do is to give it a try and see how you feel using it. Thanks to the team who built this, for all of the explanations and support, and especially, for sitting and listening to my dumb questions for 2 hours while I tested this.

Santiago

211,985 просмотров • 1 год назад

"You know, I don't, I have not changed. I really make the movies for myself. I really, really do." Q: "For no one else, or just sort of like what you ultimately want to see in them?" "Yeah, I think so." Q: "As a fan yourself, too? "What I want to see, yeah, like as a, like, you only have the benchmark of yourself. Like, if you ever try and make a movie for someone other than yourself... I feel like you're going to blow it. "Because you can't, you don't know how anyone else is going to feel. So like, you know, you go, 'okay, do I find that emotionally real? Do I find that interesting? Is that the Krypton I want to go to? Is that the Superman I want to see fight?' "You know, those are the questions you ask yourself constantly. And I think once you, if you're constantly answering yes to that, then you'll end up the more, the film will end up being more interesting to you. "And ultimately, the film being interesting to you allows you to make the movie better because you're interested. "If you make it for someone else over a two-year period, you're just going to not give a sh*t at some point because you're just like, 'I don't care. This is not my movie. I don't care about this movie because I made it for someone else.'" Q: "I imagine that's a very hard thing to do in Hollywood, though, is to keep your vision clear with so much collaboration, with so much going on, with so many other people in the mix." "It really depends on the project. For instance, it was hard on Guardians, you know, where I feel like what ended up happening on that movie was people, we did end up, they did end up asking me like, 'this is for kids, right?' "And I got to honestly say that I knew it was for kids, but I didn't want to make it for kids. You know what I mean? And I think that's what happened to that movie. It did get like second guessed at the end and turned more into a movie for kids. "My point of view is I can think like a child if I want. I have that enthusiasm for movies and what I think is cool. You, the collective you, don't need to try and second guess me and go, 'this is what we think a kid would like.' "And then it's like, 'oh, a song' or whatever. Then you're just like, 'okay, whatever.'"

"You know, I don't, I have not changed. I really make the movies for myself. I really, really do." Q: "For no one else, or just sort of like what you ultimately want to see in them?" "Yeah, I think so." Q: "As a fan yourself, too? "What I want to see, yeah, like as a, like, you only have the benchmark of yourself. Like, if you ever try and make a movie for someone other than yourself... I feel like you're going to blow it. "Because you can't, you don't know how anyone else is going to feel. So like, you know, you go, 'okay, do I find that emotionally real? Do I find that interesting? Is that the Krypton I want to go to? Is that the Superman I want to see fight?' "You know, those are the questions you ask yourself constantly. And I think once you, if you're constantly answering yes to that, then you'll end up the more, the film will end up being more interesting to you. "And ultimately, the film being interesting to you allows you to make the movie better because you're interested. "If you make it for someone else over a two-year period, you're just going to not give a sh*t at some point because you're just like, 'I don't care. This is not my movie. I don't care about this movie because I made it for someone else.'" Q: "I imagine that's a very hard thing to do in Hollywood, though, is to keep your vision clear with so much collaboration, with so much going on, with so many other people in the mix." "It really depends on the project. For instance, it was hard on Guardians, you know, where I feel like what ended up happening on that movie was people, we did end up, they did end up asking me like, 'this is for kids, right?' "And I got to honestly say that I knew it was for kids, but I didn't want to make it for kids. You know what I mean? And I think that's what happened to that movie. It did get like second guessed at the end and turned more into a movie for kids. "My point of view is I can think like a child if I want. I have that enthusiasm for movies and what I think is cool. You, the collective you, don't need to try and second guess me and go, 'this is what we think a kid would like.' "And then it's like, 'oh, a song' or whatever. Then you're just like, 'okay, whatever.'"

Zack Snyder Film

334,960 просмотров • 6 месяцев назад

Please take a minute to listen to an 18 year old Arvid Lindblad's response to a world champion asking him 'What is this world like, the F1 world? You've obviously been in F2, but this is something different altogether, the pressure it brings.' Arvid: "It is very different and to be honest it's hard for me to really answer that now because I've only done a weekend, I don't really know what it's all like but I think it's an interesting point you make on pressure because a lot of people told me and you know.. I've done one weekend I don't want to talk too much but coming into this weekend a lot of people said there's going to be a lot of pressure and all this and that. In the end, I'm here for myself, I worked my whole life to get to Formula One, I don't have to do it for anyone, I'm here for myself because when I was five years old I had a dream and my dream was to be in Formula One and I was living my dream today and I just wanted to do as best as I possibly could you know and yeah."

Please take a minute to listen to an 18 year old Arvid Lindblad's response to a world champion asking him 'What is this world like, the F1 world? You've obviously been in F2, but this is something different altogether, the pressure it brings.' Arvid: "It is very different and to be honest it's hard for me to really answer that now because I've only done a weekend, I don't really know what it's all like but I think it's an interesting point you make on pressure because a lot of people told me and you know.. I've done one weekend I don't want to talk too much but coming into this weekend a lot of people said there's going to be a lot of pressure and all this and that. In the end, I'm here for myself, I worked my whole life to get to Formula One, I don't have to do it for anyone, I'm here for myself because when I was five years old I had a dream and my dream was to be in Formula One and I was living my dream today and I just wanted to do as best as I possibly could you know and yeah."

sim 🇧🇷🇲🇽🇸🇳🇫🇷🇭🇹

886,213 просмотров • 3 месяцев назад

OpenAI launched Agents in ChatGPT today. It’s great for consumers who want to automate tasks in ChatGPT. But what if you want to build features powered by the same tools? I dropped put same demo prompt into Director, our web agent builder, to generate a script for that. Director enables anyone to build software powered by web agents. You prompt it once, and get a deterministic web agent that you can integrate into your application. It's a great starting point for building powerful buttons that do work FOR your users.

OpenAI launched Agents in ChatGPT today. It’s great for consumers who want to automate tasks in ChatGPT. But what if you want to build features powered by the same tools? I dropped put same demo prompt into Director, our web agent builder, to generate a script for that. Director enables anyone to build software powered by web agents. You prompt it once, and get a deterministic web agent that you can integrate into your application. It's a great starting point for building powerful buttons that do work FOR your users.

Paul Klein IV

32,299 просмотров • 10 месяцев назад

Jack Dorsey on becoming a better storyteller: "I found myself very early on thinking about something like thinking about this early idea for Twitter and saying to myself, I could build this awesome. You have those shower-like moments, or you're walking at midnight in some town in New York City, and you've got these amazing brand ideas. And then you start thinking, well, I could really start doing this if only X and if I had this person or if this technology existed or if this happened or this happened. And what I realized was that I was constantly making excuses for not working on it. And then the window had passed, and then I couldn't do anything. So I think it's really, really important to write it out or to draw it out or to code it. But you need to get it out of your head. And the reason you have to get it out of your head is that you need to be able to see it on a surface that is not in your mind. And once you can see it, and once you can step back from it, then you can also decide this passes my filter, my constraints, so maybe I can show it and share it with some other people. And then they will be like that's the stupidest idea ever and or that's somewhat interesting, but maybe this and this and this. So the sooner you can do that, then you have a lot of momentum around it, and you can really decide if you want to commit to it and work on it more or put it on the shelf for a later date. And the realization that I think everyone needs to have about that latter option, putting it on the shelf, is that you can come back to it and it will surface back up in another piece of work or another idea at some point in your life. So having that ability to close off a chapter and move on is really, really important. You can't have all these open threads, and that's what I realized I was doing. And that also encouraged me to really write more and to really think about what's the story? How are people coming to this? And like when I show my friends this, how are they going to react and I would write it down. I would actually treat it like a play. And when I realized that I was writing plays, I read a lot more plays for style and for substance and for technique and I think it's really good. I think there is another company that I have always looked towards for inspiration and I know a number of people in this room probably have a similar company in mind, which is Apple. Apple, I think, is run like a theater company. It has a great sense of pacing, has a great sense of story and has a great sense of execution and it's all about event-driven, it's all stage-driven, the stage being a billboard or the stage being a keynote or the stage being a product launch. All of it has a very, very cohesive end-to-end story. I mean you think about what happened when Steve Jobs came back to the company. The first thing he did was kill every product line the company was working on. And for two years,rs they had no product on the market whatsoever. All they had were a bunch of posters all around the world with Steve Jobs' heroes, and it said, think different. And it was just focused on bringing up the brand and making people aware of the brand again and how the brand is aligning to this particular feeling and story. And then they came out with the iMac and then built iTunes and then the iPod, and they realized that, wait a minute, people are carrying music on their phones now, so we better build a phone, an iPhone. And so this unfolding of the plot and the epic story has been very, very interesting to watch, especially if you look back to that time when he came back to the company. So I've learned a lot from that company and other companies that operate in a similar fashion."

Founder Mode

107,213 просмотров • 5 месяцев назад

I really, really, really wanted to drop this song last year. When I first put out the snippet, I was so excited - but it was hard to finish it on time because everything was a blur. I was sick and weak and nauseous and tired and my body just wouldn't do what I wanted it to. Even in the snippet video, I wasn't feeling great. I was just trying my best. I adore Chike's voice and I knew it was him that had to be on the song with me. When I asked him to give me a verse, he was so ready to go, but he was out of town. As soon as he came back, he came over to my studio the next day 🥹. I got a lotta respect for him. He didn't know I was pregnant and suffering 😅 Watching this video back now, I can't even understand where the energy came from. When the song was done, I struggled to mix it. Even so, I decided to master it myself. I hate mastering, so I don't know what I thinking. I was so disappointed that I couldn't meet the deadline. Everyone had fallen in love with the song and was asking me to put it out. I didn't have the energy to make content. I don't even remember them recording this video. Given how much I love this song, I'm a little bummed I couldn't give it energy it deserves. But please, know that a lot of love and resilience went into this song. I hope that you can let less be more for this one. I hope you can give it the energy that I couldn't. That I can't. PS: This is a chance for those of you that say I gave up my career for marriage to fight(?) for my uhm...rights? That or stfu. WHERE YOU DEY > Simi ft Chiké out everywhere now 🩵🩵 produced by Niphkeys mixed/mastered by Simi

I really, really, really wanted to drop this song last year. When I first put out the snippet, I was so excited - but it was hard to finish it on time because everything was a blur. I was sick and weak and nauseous and tired and my body just wouldn't do what I wanted it to. Even in the snippet video, I wasn't feeling great. I was just trying my best. I adore Chike's voice and I knew it was him that had to be on the song with me. When I asked him to give me a verse, he was so ready to go, but he was out of town. As soon as he came back, he came over to my studio the next day 🥹. I got a lotta respect for him. He didn't know I was pregnant and suffering 😅 Watching this video back now, I can't even understand where the energy came from. When the song was done, I struggled to mix it. Even so, I decided to master it myself. I hate mastering, so I don't know what I thinking. I was so disappointed that I couldn't meet the deadline. Everyone had fallen in love with the song and was asking me to put it out. I didn't have the energy to make content. I don't even remember them recording this video. Given how much I love this song, I'm a little bummed I couldn't give it energy it deserves. But please, know that a lot of love and resilience went into this song. I hope that you can let less be more for this one. I hope you can give it the energy that I couldn't. That I can't. PS: This is a chance for those of you that say I gave up my career for marriage to fight(?) for my uhm...rights? That or stfu. WHERE YOU DEY > Simi ft Chiké out everywhere now 🩵🩵 produced by Niphkeys mixed/mastered by Simi

Simi

392,492 просмотров • 4 месяцев назад

Harry about why he chose to do residencies in certain cities on Zane Lowe “I think it makes the show better. I think you can build something that doesn't have to travel every night. I think the show itself is better. I think there's something in this that allows me to like stay in my life while I'm doing it and therefore I think allows me to take care of myself better, which I think makes me better at doing the thing. It's not like I'm saying I'll never travel again, but I want to see what it looks like if you do it a different way. And you know, people in my band have like families now and kids and some aspect of that, too. It's really important to me that they're on the road that I would love to like have them and I don't want to make it like near impossible for them to be able to do that with me.”

Harry about why he chose to do residencies in certain cities on Zane Lowe “I think it makes the show better. I think you can build something that doesn't have to travel every night. I think the show itself is better. I think there's something in this that allows me to like stay in my life while I'm doing it and therefore I think allows me to take care of myself better, which I think makes me better at doing the thing. It's not like I'm saying I'll never travel again, but I want to see what it looks like if you do it a different way. And you know, people in my band have like families now and kids and some aspect of that, too. It's really important to me that they're on the road that I would love to like have them and I don't want to make it like near impossible for them to be able to do that with me.”

HSNews

282,165 просмотров • 3 месяцев назад

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."

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

62,693 просмотров • 1 месяц назад

Q: Tell me about the start then, because a lot of drivers have described it as chaos. What was your view of it and how it was handled? Charles Leclerc: Chaos. Obviously there was Lewis on the inside, which I don't think he expected that Max was on the outside of me. And so there was a little bit of contact and then I went on the dirty side of the track, no grip at all. And I couldn't really stay there as the angle with Lewis was just impossible to make a corner. So I had to go straight, but it was quite stressful. I really thought the race would end not only for me, but also for Lewis and for Max, but mostly for Lewis. Q: Are you happy with how your teammate moved at the start as well? Charles: It's racing, I think Lewis wanted to try and take his shot. I would have done exactly the same if I was him, so I have no... yeah it's completely normal. - F1 2025 Mexico -

Q: Tell me about the start then, because a lot of drivers have described it as chaos. What was your view of it and how it was handled? Charles Leclerc: Chaos. Obviously there was Lewis on the inside, which I don't think he expected that Max was on the outside of me. And so there was a little bit of contact and then I went on the dirty side of the track, no grip at all. And I couldn't really stay there as the angle with Lewis was just impossible to make a corner. So I had to go straight, but it was quite stressful. I really thought the race would end not only for me, but also for Lewis and for Max, but mostly for Lewis. Q: Are you happy with how your teammate moved at the start as well? Charles: It's racing, I think Lewis wanted to try and take his shot. I would have done exactly the same if I was him, so I have no... yeah it's completely normal. - F1 2025 Mexico -

sim

486,244 просмотров • 7 месяцев назад