正在加载视频...

视频加载失败

返回首页

Finally new version of text system is released on our website ! I released as update to old version but in reality it's completely new thing in material and lot's of work in verse. I'm still working on documentation or/and videos but here is a list of good stuff...

AsicsoN_UEFN's profile picture

AsicsoN

1,740 subscribers

12,246 次观看 • 1 个月前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Need highly optimized and functional text material? I have what you need! - Two versions available. With verse controls and static manual. - Highly optimized with relatively low instructions in material and just one texture atlas plus any custom icons images you will have. - Takes just a tiny fraction of project size and in-game memory. - Verse version supports up to 16 characters and manual one up to 12. - Highly customizable. - Verse code does all work and you just need to call functions and tell what to write. - Additional example verse device included. - Can add custom icons in all slots. No limits here. - Randomized glint included and customizable from verse too. More updates will come in future! Get it on my Patreon! #uefn #EpicPartner #uefnverse #uefnmaterial #uefntextmaterial
0:38

Need highly optimized and functional text material? I have what you need! - Two versions available. With verse controls and static manual. - Highly optimized with relatively low instructions in material and just one texture atlas plus any custom icons images you will have. - Takes just a tiny fraction of project size and in-game memory. - Verse version supports up to 16 characters and manual one up to 12. - Highly customizable. - Verse code does all work and you just need to call functions and tell what to write. - Additional example verse device included. - Can add custom icons in all slots. No limits here. - Randomized glint included and customizable from verse too. More updates will come in future! Get it on my Patreon! #uefn #EpicPartner #uefnverse #uefnmaterial #uefntextmaterial

AsicsoN

11,364 次观看 • 8 个月前

Game #1: Flappy Llama This is my first time experimenting with Scene Graph, and I absolutely love it. I can just drop down as many Flappy Llama machines as I want, and each one works as its own fully independent arcade game. Fortnite Developers #UEFN #Verse Tim Sweeney - 100% Verse UI built with Material Blocks and parameter control - Local sound effects play directly from each machine (idle SFX or gameplay triggers) - Dynamically updating leaderboard - Machine animates on player input so others see it in use (including the screen showing it’s occupied) I’m not great with materials, so huge shoutout to Blanky | R-leeo Maoate for setting me up with a simple material that had the parameters I needed to make the game work (and for helping me figure out how to decorate my fun little machine). Game #2 will be shown soon, it just needs a few final touch-ups, but I love it just as much. (here's your hint 💣🧹)
1:20

Game #1: Flappy Llama This is my first time experimenting with Scene Graph, and I absolutely love it. I can just drop down as many Flappy Llama machines as I want, and each one works as its own fully independent arcade game. Fortnite Developers #UEFN #Verse Tim Sweeney - 100% Verse UI built with Material Blocks and parameter control - Local sound effects play directly from each machine (idle SFX or gameplay triggers) - Dynamically updating leaderboard - Machine animates on player input so others see it in use (including the screen showing it’s occupied) I’m not great with materials, so huge shoutout to Blanky | R-leeo Maoate for setting me up with a simple material that had the parameters I needed to make the game work (and for helping me figure out how to decorate my fun little machine). Game #2 will be shown soon, it just needs a few final touch-ups, but I love it just as much. (here's your hint 💣🧹)

DolphinDom 🐬 | Dominic Catelani

18,788 次观看 • 7 个月前

🚨 “Utah is planning on taking water away from farmers and ranchers right now” “They are currently writing new legislation that is going to put new regulations on farmers and ranchers water use — We need your help. We need to save the farmers and ranchers” “The verbiage in the bill is that they are going to require them to use less water, water that has been already granted to them from generations past, or they're going to require them to use more water saving technologies. But who is going to pay for that? It sure as hell isn't going to be the legislators, it's not going to be the senators, it's not going to be the governor. It's going to be the taxpayers and the farmers and ranchers who are going to have to equip for this. So right now we need your help. We need you to call all of the state senators, we need to call all the city offices, we need to send as many emails as we possibly can. Leave the farmers out of this bill. There should be no reason that they're included in this whatsoever —- So if you guys can please make the calls, please send the emails. We need your help.” ‘The Utah farmers and ranchers truly need your help. We barely have enough water as it is to raise our crops to feed and grow our animals. If there is any more regulation, we will lose more and more and more of our family farms and ranches. They will not be able to survive this. This is just a stepping stone and if it happens in one place, it will continue to happen all across the nation please if you can share with your family and friends please leave your comments below. We need your help.”
1:15

🚨 “Utah is planning on taking water away from farmers and ranchers right now” “They are currently writing new legislation that is going to put new regulations on farmers and ranchers water use — We need your help. We need to save the farmers and ranchers” “The verbiage in the bill is that they are going to require them to use less water, water that has been already granted to them from generations past, or they're going to require them to use more water saving technologies. But who is going to pay for that? It sure as hell isn't going to be the legislators, it's not going to be the senators, it's not going to be the governor. It's going to be the taxpayers and the farmers and ranchers who are going to have to equip for this. So right now we need your help. We need you to call all of the state senators, we need to call all the city offices, we need to send as many emails as we possibly can. Leave the farmers out of this bill. There should be no reason that they're included in this whatsoever —- So if you guys can please make the calls, please send the emails. We need your help.” ‘The Utah farmers and ranchers truly need your help. We barely have enough water as it is to raise our crops to feed and grow our animals. If there is any more regulation, we will lose more and more and more of our family farms and ranches. They will not be able to survive this. This is just a stepping stone and if it happens in one place, it will continue to happen all across the nation please if you can share with your family and friends please leave your comments below. We need your help.”

Wall Street Apes

107,092 次观看 • 10 个月前

You can attach your own files as custom instructions to GitHub Copilot. They don't need to be text, either! You can use code, such as SQL, or templates in any language you're working with.
0:59

You can attach your own files as custom instructions to GitHub Copilot. They don't need to be text, either! You can use code, such as SQL, or templates in any language you're working with.

Visual Studio Code

48,678 次观看 • 1 年前

I made a few updates to the MLX port of F5 TTS over the holiday: - Longform generation is now supported, and text will be split automatically on sentence boundaries for natural-sounding speech. - You can now pipe in text from another process (e.g. a language model) and listen to the speech as each segment is generated. - I implemented RK4 sampling for the ODE, which achieves much better quality with fewer steps — it's now possible to generate speech at 1.6x realtime on my M3 Max. See the video of an example of generating speech in realtime from a language model entirely on-device! 🚀
0:54

I made a few updates to the MLX port of F5 TTS over the holiday: - Longform generation is now supported, and text will be split automatically on sentence boundaries for natural-sounding speech. - You can now pipe in text from another process (e.g. a language model) and listen to the speech as each segment is generated. - I implemented RK4 sampling for the ODE, which achieves much better quality with fewer steps — it's now possible to generate speech at 1.6x realtime on my M3 Max. See the video of an example of generating speech in realtime from a language model entirely on-device! 🚀

Lucas Newman

22,962 次观看 • 1 年前

LATENT SPACE TERMINAL Demo v0.09 The vision behind LST is to create a portal into the multi-verse where you can explore new worlds and alternate realities. And I do mean *any* world or reality. You can basically type in anything, just like you would with ChatGPT or MidJourney, and what you get is not a single text response or image or video, but a whole world. This is a very early look at how LST is developing. There is still a lot more work to do but as with all of my projects, I like building in public. The demo shows three prompts: “space pirates”, “scary mystery story about a man eating a pickle”, “fpv shot of a passenger on a sailboat in the ocean”. I only traverse down one level in the video but each world has an infinite number of levels you can go down. Everything is generated by AI from the story to the videos to the audio. Right now, it works well on two ends of the spectrum. The weirder the better or the more realistic/documentary-like the better. Still very early, but so far it looks promising.
2:27

LATENT SPACE TERMINAL Demo v0.09 The vision behind LST is to create a portal into the multi-verse where you can explore new worlds and alternate realities. And I do mean *any* world or reality. You can basically type in anything, just like you would with ChatGPT or MidJourney, and what you get is not a single text response or image or video, but a whole world. This is a very early look at how LST is developing. There is still a lot more work to do but as with all of my projects, I like building in public. The demo shows three prompts: “space pirates”, “scary mystery story about a man eating a pickle”, “fpv shot of a passenger on a sailboat in the ocean”. I only traverse down one level in the video but each world has an infinite number of levels you can go down. Everything is generated by AI from the story to the videos to the audio. Right now, it works well on two ends of the spectrum. The weirder the better or the more realistic/documentary-like the better. Still very early, but so far it looks promising.

Chikai

12,283 次观看 • 1 年前

A closer look on the GSAP powered animations in Webflow. Just from my perspective. In short, it’s way more powerful than I first thought. The more I use it, the more I like it. Of course, there are some parts missing. But it's the first version. There's still a lot to come. For example, custom ease would already make a huge difference. Breakpoints. Maybe a way to add custom functions as sometimes you need to calculate stuff in JavaScript to get complex animations. The biggest part for me is that you can just build the animation inside a timeline. This makes it so much easier than writing it as code. You can fine tune it so much more. When there would be a way to export the tween as code to add some more functionality would be awesome. You can also add custom classes with the timeline, which can then be used in custom CSS to add more functionality. With a bit of custom code you can also use breakpoints for your animations. By using the custom event the animation can be used in custom code which can also be pretty powerful. Didn’t test it so much yet, but would be cool if you could just take the event and use for example the onComplete() from GSAP or other stuff. For example. let mm = gsap.matchMedia(); const module = Webflow.require("ix3"); module.ready().then(() => { mm.add( { isMobile: "(max-width: 992px)", }, (context) => { let { isMobile } = context.conditions; if (isMobile) { module.emit("Mobile Animation"); } } ); }); "Mobile Animation" is the name of your custom event. I hope that part will get more powerful. Something I miss on the timeline is that when you select more actions you can just drag all actions. It would be cool if you could move it frame by frame with the arrow keys, like in Jitter for example. Or just write a specific point like when you have one selected. For now I would further write the code myself, but I’m excited to see where it’s going. Maybe there will be a time where you could animate most parts inside Webflow 🙂 Can’t wait for the next GSAP update!
0:27

A closer look on the GSAP powered animations in Webflow. Just from my perspective. In short, it’s way more powerful than I first thought. The more I use it, the more I like it. Of course, there are some parts missing. But it's the first version. There's still a lot to come. For example, custom ease would already make a huge difference. Breakpoints. Maybe a way to add custom functions as sometimes you need to calculate stuff in JavaScript to get complex animations. The biggest part for me is that you can just build the animation inside a timeline. This makes it so much easier than writing it as code. You can fine tune it so much more. When there would be a way to export the tween as code to add some more functionality would be awesome. You can also add custom classes with the timeline, which can then be used in custom CSS to add more functionality. With a bit of custom code you can also use breakpoints for your animations. By using the custom event the animation can be used in custom code which can also be pretty powerful. Didn’t test it so much yet, but would be cool if you could just take the event and use for example the onComplete() from GSAP or other stuff. For example. let mm = gsap.matchMedia(); const module = Webflow.require("ix3"); module.ready().then(() => { mm.add( { isMobile: "(max-width: 992px)", }, (context) => { let { isMobile } = context.conditions; if (isMobile) { module.emit("Mobile Animation"); } } ); }); "Mobile Animation" is the name of your custom event. I hope that part will get more powerful. Something I miss on the timeline is that when you select more actions you can just drag all actions. It would be cool if you could move it frame by frame with the arrow keys, like in Jitter for example. Or just write a specific point like when you have one selected. For now I would further write the code myself, but I’m excited to see where it’s going. Maybe there will be a time where you could animate most parts inside Webflow 🙂 Can’t wait for the next GSAP update!

Eduard Bodak

12,590 次观看 • 10 个月前

AudioLink Plugin for Warudo is now available! You can grab it in my Vgen store. Should just work for most cases! As long as the character or environment are setup to use AudioLink. Same process and system as VRChat! Works in both the free and paid versions of Warudo. To help this post in the algorithm please let me know any features you'd like added or any questions you have in the comments below! Looking forward to seeing how people use it!
0:47

AudioLink Plugin for Warudo is now available! You can grab it in my Vgen store. Should just work for most cases! As long as the character or environment are setup to use AudioLink. Same process and system as VRChat! Works in both the free and paid versions of Warudo. To help this post in the algorithm please let me know any features you'd like added or any questions you have in the comments below! Looking forward to seeing how people use it!

Bamfy Jifu - 3D Artist

39,772 次观看 • 5 个月前

New short course: Collaborative Writing and Coding with OpenAI Canvas! Explore new ways to write and code with OpenAI Canvas, a user-friendly interface that allows you to brainstorm, draft, and refine text and code in collaboration with ChatGPT. In the short course, created with OpenAI, and taught by , a research lead at OpenAI, you’ll learn to use Canvas to enhance your workflows. Canvas lets you go beyond simple chat interactions. It provides a side-by-side workspace where you and ChatGPT can edit and refine text or code collaboratively. This makes brainstorming, drafting, and iterating as you write feel more natural and effective. As the first major update to ChatGPT’s visual interface since its launch in 2022, Canvas gives a new, innovative approach to collaboration with AI. For instance, after writing the first version of your code, Canvas can review it and give suggestions for improvement. It can also help with debugging by adding logging, identifying problems to fix, and writing comments. In addition, you'll also learn what it takes to train the model for an interface like Canvas. In this video-only short course, you’ll: - Learn how to ask for in-line feedback and control the iteration of your work by directly editing selected areas of your text or code from the model’s output. - Learn how to access quick automation tools in a shortcut menu that allows you to modify your writing tone and length, enhance your code, and restore previous versions of your work. - Learn how to use Canvas as a research assistant tool with an example of asking the model to reason through the screenshot of a plot to write a research report, in which you can ask questions within the created report. - Ask the model to write Python code to replicate the graph seen on a screenshot image. - Go behind the scenes of how you can create a video game, such as Space Battleship, from scratch, edit it, and display it in one self-contained HTML file. - Get a real-world application example of creating a SQL database from the image of its architecture. - Understand the model training and design processes that power Canvas! Please sign up here:
1:49

New short course: Collaborative Writing and Coding with OpenAI Canvas! Explore new ways to write and code with OpenAI Canvas, a user-friendly interface that allows you to brainstorm, draft, and refine text and code in collaboration with ChatGPT. In the short course, created with OpenAI, and taught by , a research lead at OpenAI, you’ll learn to use Canvas to enhance your workflows. Canvas lets you go beyond simple chat interactions. It provides a side-by-side workspace where you and ChatGPT can edit and refine text or code collaboratively. This makes brainstorming, drafting, and iterating as you write feel more natural and effective. As the first major update to ChatGPT’s visual interface since its launch in 2022, Canvas gives a new, innovative approach to collaboration with AI. For instance, after writing the first version of your code, Canvas can review it and give suggestions for improvement. It can also help with debugging by adding logging, identifying problems to fix, and writing comments. In addition, you'll also learn what it takes to train the model for an interface like Canvas. In this video-only short course, you’ll: - Learn how to ask for in-line feedback and control the iteration of your work by directly editing selected areas of your text or code from the model’s output. - Learn how to access quick automation tools in a shortcut menu that allows you to modify your writing tone and length, enhance your code, and restore previous versions of your work. - Learn how to use Canvas as a research assistant tool with an example of asking the model to reason through the screenshot of a plot to write a research report, in which you can ask questions within the created report. - Ask the model to write Python code to replicate the graph seen on a screenshot image. - Go behind the scenes of how you can create a video game, such as Space Battleship, from scratch, edit it, and display it in one self-contained HTML file. - Get a real-world application example of creating a SQL database from the image of its architecture. - Understand the model training and design processes that power Canvas! Please sign up here:

Andrew Ng

128,085 次观看 • 1 年前

CSS Tip! ⭐️ You can use the lh (line-height) unit on background layers to emphasize multiple lines of text responsively without extra elements! ⚡️ h1 { background: linear-gradient(white, white), grey; background-size: 100% calc(var(--lines) * 1lh), 100% 100%; background-clip: text; color: transparent; } Here you emphasize the first two lines of the heading with white using a sized background-image layer It has a size of 2lh ✨ Then the rest of the element is colored with whatever other colors you want to use as layers. If you watch the video, you can see different colors used for different lines and then fade it out if you wish. You could do whatever you like with it 😎 Neat part is that it's responsive. The font-size is set with a clamp and you can resize the viewport or the element and the number of lines emphasized will remain 🤙 Last but not least, make sure to use background-clip: text and color: transparent so the background shines through 🔥 Also, note that if you're only looking to highlight the first line, you can still use the :first-line pseudo 🫶 Have a play with it and see what you can come up with! CodePen.IO link below! 👇
0:57

CSS Tip! ⭐️ You can use the lh (line-height) unit on background layers to emphasize multiple lines of text responsively without extra elements! ⚡️ h1 { background: linear-gradient(white, white), grey; background-size: 100% calc(var(--lines) * 1lh), 100% 100%; background-clip: text; color: transparent; } Here you emphasize the first two lines of the heading with white using a sized background-image layer It has a size of 2lh ✨ Then the rest of the element is colored with whatever other colors you want to use as layers. If you watch the video, you can see different colors used for different lines and then fade it out if you wish. You could do whatever you like with it 😎 Neat part is that it's responsive. The font-size is set with a clamp and you can resize the viewport or the element and the number of lines emphasized will remain 🤙 Last but not least, make sure to use background-clip: text and color: transparent so the background shines through 🔥 Also, note that if you're only looking to highlight the first line, you can still use the :first-line pseudo 🫶 Have a play with it and see what you can come up with! CodePen.IO link below! 👇

jhey ʕ•ᴥ•ʔ

413,647 次观看 • 2 年前

hidream-edit is now on FAL i'm pretty sure it is the fastest out there and it supports streaming as well, you can give it any image along with your text instruction to edit, and it will generate the final result in only around 17 seconds!
0:21

hidream-edit is now on FAL i'm pretty sure it is the fastest out there and it supports streaming as well, you can give it any image along with your text instruction to edit, and it will generate the final result in only around 17 seconds!

maharshi

17,807 次观看 • 1 年前

Our text-to-image got faster, better and photorealistic 😎 You can generate images in real-time, with an infinite scroll, and ready-to-use prompts and styles. The upgraded version is now available for AI partners and premium users.
0:41

Our text-to-image got faster, better and photorealistic 😎 You can generate images in real-time, with an infinite scroll, and ready-to-use prompts and styles. The upgraded version is now available for AI partners and premium users.

Freepik

4,733,219 次观看 • 2 年前

“i’ve been told that you've tried spending less time on your phone recently, which i believe is a very hard thing to do. what made you do it? and did it actually work?” 🆑: yeah, i am achieving that. then there's a balance to find, because it's also true that as soon as you are... you kind of feel a little bit disconnected on what's going around because today everybody is with a phone, and so there's a balance to find. i did two or three months, i think, without ever touching my phone apart from whatsapp when i was receiving messages and calls, and that was maybe a little bit extreme. so now maybe i'm trying to find a balance between the two because it's good to be up to date with what's going on around the world and to stay in touch with friends and funny moments. there's also lots of funny moments on social media and it part also of social interaction with friends and family. so there's a balance to find, but it is also true that it's a place where sometimes it can be a little bit toxic when you are in a position where people can kind of judge and say anything very, very easily. and they have the right to do so, but as a human being, you can also be affected by looking at those things. so it's a balance to find. i don't know if i found the perfect one, but for now it works for me, which is the most important.
1:22

“i’ve been told that you've tried spending less time on your phone recently, which i believe is a very hard thing to do. what made you do it? and did it actually work?” 🆑: yeah, i am achieving that. then there's a balance to find, because it's also true that as soon as you are... you kind of feel a little bit disconnected on what's going around because today everybody is with a phone, and so there's a balance to find. i did two or three months, i think, without ever touching my phone apart from whatsapp when i was receiving messages and calls, and that was maybe a little bit extreme. so now maybe i'm trying to find a balance between the two because it's good to be up to date with what's going on around the world and to stay in touch with friends and funny moments. there's also lots of funny moments on social media and it part also of social interaction with friends and family. so there's a balance to find, but it is also true that it's a place where sometimes it can be a little bit toxic when you are in a position where people can kind of judge and say anything very, very easily. and they have the right to do so, but as a human being, you can also be affected by looking at those things. so it's a balance to find. i don't know if i found the perfect one, but for now it works for me, which is the most important.

clara

15,738 次观看 • 2 天前

✨ 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

640,316 次观看 • 4 个月前

As many of you know, for the last five months I've been working full-time on my next big thing. The challenge was to invent something new and implement it entirely using LLMs for writing code. The first stage of the project is now complete: the web application, which I called is now online and accepting users. You can see a short demo in the video. 100% of the code of the app was generated by LLMs (mostly Gemini and Claude, maybe 10% of ChatGPT). I haven't written a single line of code. The tech stack is TypeScript, React, and Supabase/Postgres which was (and still is) fully new to me. During these five months, I implemented from scratch three versions of the software. It started as a Markdown editor to help me with my book writing and ended up as an AI-assisted reading and self-learning platform. What makes ChapterPal unique is a novel reading experience where the user can use the keyboard keys to reveal or "unreveal" the content and ask questions at any moment. (Mouse wheel, touchpad, smartphone screen, and voice input are also supported.) The LLM receives the entire content of the chapter and tries to answer questions based on the chapter's content, which reduces the chance of hallucination to the minimum. (Though not to 0%, of course, but near it.) This way of content consumption is known as **active reading,** a strategy for engaging with a text to improve comprehension and retention by consciously interacting with the material. The goal is to move beyond passive reading to a deeper understanding of the text and to remember key information more effectively. The registration on ChapterPal is via the waiting list. This is to avoid unexpected load spikes and cloud charges. Usually, it takes less than 24 hours for me to activate a user. Give it a try and let me know what you think. The next stage is finishing the content ingestion pipeline, which will automatically convert high-quality content from sources like HTML, PDF, and LaTeX into Markdown. Obviously, only those pieces whose licenses allow creating copies. ChapterPal has its own collection of textbooks and articles on AI, machine learning, and data science topics. If you don't find a piece of content you would like to read in ChapterPal's collection, a Chrome extension, ChapterPal Uploader, allows you to upload any PDF or HTML page to ChapterPal in one click. The content is only available for you to read to avoid the possibility of copyright infringement. I hope you enjoy using it as much as I enjoy building it.
3:41

As many of you know, for the last five months I've been working full-time on my next big thing. The challenge was to invent something new and implement it entirely using LLMs for writing code. The first stage of the project is now complete: the web application, which I called is now online and accepting users. You can see a short demo in the video. 100% of the code of the app was generated by LLMs (mostly Gemini and Claude, maybe 10% of ChatGPT). I haven't written a single line of code. The tech stack is TypeScript, React, and Supabase/Postgres which was (and still is) fully new to me. During these five months, I implemented from scratch three versions of the software. It started as a Markdown editor to help me with my book writing and ended up as an AI-assisted reading and self-learning platform. What makes ChapterPal unique is a novel reading experience where the user can use the keyboard keys to reveal or "unreveal" the content and ask questions at any moment. (Mouse wheel, touchpad, smartphone screen, and voice input are also supported.) The LLM receives the entire content of the chapter and tries to answer questions based on the chapter's content, which reduces the chance of hallucination to the minimum. (Though not to 0%, of course, but near it.) This way of content consumption is known as **active reading,** a strategy for engaging with a text to improve comprehension and retention by consciously interacting with the material. The goal is to move beyond passive reading to a deeper understanding of the text and to remember key information more effectively. The registration on ChapterPal is via the waiting list. This is to avoid unexpected load spikes and cloud charges. Usually, it takes less than 24 hours for me to activate a user. Give it a try and let me know what you think. The next stage is finishing the content ingestion pipeline, which will automatically convert high-quality content from sources like HTML, PDF, and LaTeX into Markdown. Obviously, only those pieces whose licenses allow creating copies. ChapterPal has its own collection of textbooks and articles on AI, machine learning, and data science topics. If you don't find a piece of content you would like to read in ChapterPal's collection, a Chrome extension, ChapterPal Uploader, allows you to upload any PDF or HTML page to ChapterPal in one click. The content is only available for you to read to avoid the possibility of copyright infringement. I hope you enjoy using it as much as I enjoy building it.

BURKOV

81,150 次观看 • 7 个月前

I just released a beta version of /dev/push. It's basically a (simpler) alternative to Vercel, Render, and the likes. You can log in with GitHub, pick a repo, configure your build and off you go. Whenever you push code to GitHub it will automatically deploy it for you. There's obviously more to it: environments, custom domains, environment variables, custom commands, teams... And I'm working on adding more: custom Docker containers, remote nodes, SQLite database, support for PHP, RoR... It's completely free and open source (MIT license). The online version is for now restricted as I test things up. Links below👇
2:33

I just released a beta version of /dev/push. It's basically a (simpler) alternative to Vercel, Render, and the likes. You can log in with GitHub, pick a repo, configure your build and off you go. Whenever you push code to GitHub it will automatically deploy it for you. There's obviously more to it: environments, custom domains, environment variables, custom commands, teams... And I'm working on adding more: custom Docker containers, remote nodes, SQLite database, support for PHP, RoR... It's completely free and open source (MIT license). The online version is for now restricted as I test things up. Links below👇

Ronan Berder

21,938 次观看 • 9 个月前

✨ has now gone from $0 to $1 million ARR in just 17 days! 💸 Revenue update: $87,000 MRR (which is $1M ARR) My first project ever to go up this fast 🤯 Only 3 ads left now: 📊 Stats update: 320,000 people have now flown in the game Whether the MRR is truly sustainable for a year we can only guess, but they ARE subscriptions and they do renew so as long as the game keeps improving it might happen? 🛸 Since I kept getting hacked by UFO invaders, I decide to sell the UFOs, and coincidentally new sponsor Basecamp wanted an UFO as the origin of 37 Signals (their original company name) comes from the 37 radio signals detected from space to detect extraterrestrial life, so I built them a custom UFO with their original snow globe logo on top which you can see flying around below And I have one new sponsor that sells Ozempic so got the text on the blimp "are you as big as a blimp? lose weight at 😂 I was ski'ing today so was AFK mostly but I did: ✅ Fix more XSS issues, which to be fair unless you explicitly ask it to find every single XSS loophole, AI doesn't really care about when it writes code, so you really gotta ask it to extra check your code cause honestly it can be full of security holes One unlucky (or lucky) thing is that this project took off completely unpredicted and it happened just when I was on travel with gf to France and Switzerland. I didn't wanna lock myself up in a room all day computering so I actually spend most of the days just doing fun stuff with her (as I should) and then in the evening when I got an hour (like now), scrambling and quickly getting things done That would never be possible if I coded it without AI though, it would simply take too much time. Without AI it would have taken me 10-100x more time and I would have simply not been able to build this and maintain it at the same speed AI really is a creativity and speed maximizer for me, making me just way more creative and more fast I still mostly use Cursor + Anthropic Claude 3.5 and trying 3.7 too now! I'm excited to get more time in the next few days so I can really add some new things, one thing I want is to put a big 3d leaderboard INSIDE the game with the scores on it for example
0:57

✨ has now gone from $0 to $1 million ARR in just 17 days! 💸 Revenue update: $87,000 MRR (which is $1M ARR) My first project ever to go up this fast 🤯 Only 3 ads left now: 📊 Stats update: 320,000 people have now flown in the game Whether the MRR is truly sustainable for a year we can only guess, but they ARE subscriptions and they do renew so as long as the game keeps improving it might happen? 🛸 Since I kept getting hacked by UFO invaders, I decide to sell the UFOs, and coincidentally new sponsor Basecamp wanted an UFO as the origin of 37 Signals (their original company name) comes from the 37 radio signals detected from space to detect extraterrestrial life, so I built them a custom UFO with their original snow globe logo on top which you can see flying around below And I have one new sponsor that sells Ozempic so got the text on the blimp "are you as big as a blimp? lose weight at 😂 I was ski'ing today so was AFK mostly but I did: ✅ Fix more XSS issues, which to be fair unless you explicitly ask it to find every single XSS loophole, AI doesn't really care about when it writes code, so you really gotta ask it to extra check your code cause honestly it can be full of security holes One unlucky (or lucky) thing is that this project took off completely unpredicted and it happened just when I was on travel with gf to France and Switzerland. I didn't wanna lock myself up in a room all day computering so I actually spend most of the days just doing fun stuff with her (as I should) and then in the evening when I got an hour (like now), scrambling and quickly getting things done That would never be possible if I coded it without AI though, it would simply take too much time. Without AI it would have taken me 10-100x more time and I would have simply not been able to build this and maintain it at the same speed AI really is a creativity and speed maximizer for me, making me just way more creative and more fast I still mostly use Cursor + Anthropic Claude 3.5 and trying 3.7 too now! I'm excited to get more time in the next few days so I can really add some new things, one thing I want is to put a big 3d leaderboard INSIDE the game with the scores on it for example

@levelsio

2,404,766 次观看 • 1 年前

Don't use ChatGPT for academic writing. It may get flagged as AI-generated text. Instead, use Paperpal — an AI-powered personal writing assistant. Especially if your first language is not English. Think of Paperl as the elder brother of Grammarly, especially designed for academic writing. Go to and sign up. You can either start writing in Paperpal or paste a text you have already written. Paperpal will evaluate your writing and give you detailed suggestions to improve it. If English is not your first language, you can write in your own language and Paperpal will translate it for you. You can also install a Paperpal add-in in MS Word. Click on "Insert" and then "Get Add-ins." Search for the Paperpal add-in, and press "Add." And you will have Paperpal inside MS Word. Paperpal will give you helpful suggestion as you write. You can write in your own language and get Paperpal to translate it into English. Paperpal supports following languages: Bulgarian, Chinese, Czech, Danish, Dutch, Estonian, Finnish, French, German, Greek, Hungarian, Indonesian, Italian, Japanese, Korean, Latvian, Lithuanian, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Turkish, Ukrainian. Please note Paperpal's give you 500 free suggestions a month after which you will have to buy a subscription. If you use it judiciously, you won't have to pay any money. ----- Found this post helpful? 1. Retweet to share it with your friends. 2. Bookmark it so you can come back to it later. 3. Follow me for regular posts on how to supercharge your academic writing with AI-powered apps.
0:25

Don't use ChatGPT for academic writing. It may get flagged as AI-generated text. Instead, use Paperpal — an AI-powered personal writing assistant. Especially if your first language is not English. Think of Paperl as the elder brother of Grammarly, especially designed for academic writing. Go to and sign up. You can either start writing in Paperpal or paste a text you have already written. Paperpal will evaluate your writing and give you detailed suggestions to improve it. If English is not your first language, you can write in your own language and Paperpal will translate it for you. You can also install a Paperpal add-in in MS Word. Click on "Insert" and then "Get Add-ins." Search for the Paperpal add-in, and press "Add." And you will have Paperpal inside MS Word. Paperpal will give you helpful suggestion as you write. You can write in your own language and get Paperpal to translate it into English. Paperpal supports following languages: Bulgarian, Chinese, Czech, Danish, Dutch, Estonian, Finnish, French, German, Greek, Hungarian, Indonesian, Italian, Japanese, Korean, Latvian, Lithuanian, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Turkish, Ukrainian. Please note Paperpal's give you 500 free suggestions a month after which you will have to buy a subscription. If you use it judiciously, you won't have to pay any money. ----- Found this post helpful? 1. Retweet to share it with your friends. 2. Bookmark it so you can come back to it later. 3. Follow me for regular posts on how to supercharge your academic writing with AI-powered apps.

Mushtaq Bilal, PhD

344,356 次观看 • 3 年前

Elon Musk: You can also ask Grok about anything you see on the platform. You just press the Grok icon on any X post and it'll analyze it for you and research it as much as you want So you can basically have, just by tapping the Grok icon, you can assess whether that post is the truth, the whole truth, or nothing but the truth, or whether there's something supplemental or needs to be explained I think we've made a lot of progress towards freedom of speech and people being able to tell whether something is false or not false or propaganda. The recent update to Grok it's actually very good at piercing through propaganda And then we use that latest version of Grok to create Grokipedia, which I think is a much more, it's not just, I think, more neutral and more accurate than Wikipedia, but it actually has a lot more information than a Wikipedia page
1:06

Elon Musk: You can also ask Grok about anything you see on the platform. You just press the Grok icon on any X post and it'll analyze it for you and research it as much as you want So you can basically have, just by tapping the Grok icon, you can assess whether that post is the truth, the whole truth, or nothing but the truth, or whether there's something supplemental or needs to be explained I think we've made a lot of progress towards freedom of speech and people being able to tell whether something is false or not false or propaganda. The recent update to Grok it's actually very good at piercing through propaganda And then we use that latest version of Grok to create Grokipedia, which I think is a much more, it's not just, I think, more neutral and more accurate than Wikipedia, but it actually has a lot more information than a Wikipedia page

X Freeze

22,370,756 次观看 • 7 个月前

Fiverr just launched a platform for freelancers to train a custom AI model, and "sell" the ability to generate work with it. They're pitching it as a way for creators to scale the number of projects they can handle at once. Models are trainable on text, image, and sound.
0:24

Fiverr just launched a platform for freelancers to train a custom AI model, and "sell" the ability to generate work with it. They're pitching it as a way for creators to scale the number of projects they can handle at once. Models are trainable on text, image, and sound.

Olivia Moore

117,853 次观看 • 1 年前