正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

I've built a bunch of tools this summer to move my whole workflow to using things that are "pure text" so I can use AI on top. Here's the first: a modern paper reader. PDFs suck. Ugly, terribly interface, big files, fixed. I want papers that are adaptive, interactive,... show more

Kevin A. Bryan

20,908 subscribers

23,310 次观看 • 1 年前 •via X (Twitter)

健康养生科学技术教育

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

I built a Nous Research Hermes workflow that my team at Box uses to track AI trends. Every day at 7am, it researches what's happening across the AI ecosystem and generates a brief for our team. We use it to identify: • AI trends worth paying attention to • Open source projects gaining momentum • New tools developers are adopting • Content opportunities to work on next I've been building agentic workflows for months, and this is one I've actually integrated into my team's daily workflow. Here's how I built it:

I built a Nous Research Hermes workflow that my team at Box uses to track AI trends. Every day at 7am, it researches what's happening across the AI ecosystem and generates a brief for our team. We use it to identify: • AI trends worth paying attention to • Open source projects gaining momentum • New tools developers are adopting • Content opportunities to work on next I've been building agentic workflows for months, and this is one I've actually integrated into my team's daily workflow. Here's how I built it:

Chris Kim

78,552 次观看 • 1 个月前

Standard Intelligence's devansh responds to roon's tweet that "text is the universal interface," and explains why their new foundation model is trained on video: "At some point in the arbitrarily long future, if we only use text models, we could force most things to be text. But I think there are just a lot of things that are much more native when done from a computer-use [perspective]." "GUIs are designed for humans to use. We have this massive long tail of things on the internet that are entirely undoable by LLMs." "For example, when I do ML engineering most of my time is spent doing the grunt work of engineering. It's a lot of looking at graphs, analyzing, and comparing loss curves. You can do this in text, but it's a much larger pain than doing it in the native interface." "There's a reason humans don't interact with a computer purely through text, it would kind of suck."

Standard Intelligence's devansh responds to roon's tweet that "text is the universal interface," and explains why their new foundation model is trained on video: "At some point in the arbitrarily long future, if we only use text models, we could force most things to be text. But I think there are just a lot of things that are much more native when done from a computer-use [perspective]." "GUIs are designed for humans to use. We have this massive long tail of things on the internet that are entirely undoable by LLMs." "For example, when I do ML engineering most of my time is spent doing the grunt work of engineering. It's a lot of looking at graphs, analyzing, and comparing loss curves. You can do this in text, but it's a much larger pain than doing it in the native interface." "There's a reason humans don't interact with a computer purely through text, it would kind of suck."

TBPN

64,434 次观看 • 5 个月前

Most AI video apps are slop machines So we built the platform professional AI filmmakers actually want to use This is Preview, a preview for Preview made on a platform called Preview. Here's how I made preview in 3 days using Preview 👇

Most AI video apps are slop machines So we built the platform professional AI filmmakers actually want to use This is Preview, a preview for Preview made on a platform called Preview. Here's how I made preview in 3 days using Preview 👇

Kyle Salazar

10,617 次观看 • 6 个月前

This is next level teaching content. I created this video [click to play 👇] in 4 steps and 8 minutes using these AI tools: ChatGPT - Script Midjourney - Image Play(dot)ht - Voice D-ID - Animation Here's my workflow, so that you can do it too.

This is next level teaching content. I created this video [click to play 👇] in 4 steps and 8 minutes using these AI tools: ChatGPT - Script Midjourney - Image Play(dot)ht - Voice D-ID - Animation Here's my workflow, so that you can do it too.

Dan Fitzpatrick

153,339 次观看 • 3 年前

I just deployed a token on Abstract using only my voice, using AI agents. I built an open-source Discord bot that controls a wallet, can perform on-chain actions, and replies to users in the voice chat. Here's a demo:

I just deployed a token on Abstract using only my voice, using AI agents. I built an open-source Discord bot that controls a wallet, can perform on-chain actions, and replies to users in the voice chat. Here's a demo:

Jarrod Watts

131,616 次观看 • 1 年前

I've changed how I build software, from the tech stack I use to the tools I use. I've been so productive that I'll be launching 4 apps in the next month and a half. Let's talk about this change

I've changed how I build software, from the tech stack I use to the tools I use. I've been so productive that I'll be launching 4 apps in the next month and a half. Let's talk about this change

Micky

17,581 次观看 • 4 个月前

Most people use AI tools separately. Arcads lets you integrate them into a creation system. I created a complete node-based workflow for my short film: What I still control: • writing • character design • art direction What Arcads does: • connects all the elements • structures the pipeline • ensures consistency using the best AI tools and models for generating text, images, and video Here's the difference between: → content generation → creating a production workflow Arcads offers an AI agent to automate a large part of the process. This changes the speed of creation.

Most people use AI tools separately. Arcads lets you integrate them into a creation system. I created a complete node-based workflow for my short film: What I still control: • writing • character design • art direction What Arcads does: • connects all the elements • structures the pipeline • ensures consistency using the best AI tools and models for generating text, images, and video Here's the difference between: → content generation → creating a production workflow Arcads offers an AI agent to automate a large part of the process. This changes the speed of creation.

Anima

29,450 次观看 • 3 个月前

I'm almost fine. I was bored so I improved my workflow to use MMD motions with my models by a lot. I also bought a new plugin that works for bone physics. And then I realize that MMD motions I have are... questionable, so I had to use the only sfw one I found for this teaser XD

I'm almost fine. I was bored so I improved my workflow to use MMD motions with my models by a lot. I also bought a new plugin that works for bone physics. And then I realize that MMD motions I have are... questionable, so I had to use the only sfw one I found for this teaser XD

BanchouForte - 3D Modeler

24,868 次观看 • 4 个月前

Gehlee shared her thoughts about AI: "If you're using it to steal art, I don’t condone that behavior." "It can be helpful to an extent... but I dont want the world to be run by a bunch of people who cheated on their education with AI." Pure queen behavior 👸🏼

Gehlee shared her thoughts about AI: "If you're using it to steal art, I don’t condone that behavior." "It can be helpful to an extent... but I dont want the world to be run by a bunch of people who cheated on their education with AI." Pure queen behavior 👸🏼

Gehlove

454,069 次观看 • 8 个月前

Modern women on Tik Tok are now coming to the realization that they must make the first move if they want to date a top 10% man. This is a glorious sight to see, the Red pill is working 👑

Modern women on Tik Tok are now coming to the realization that they must make the first move if they want to date a top 10% man. This is a glorious sight to see, the Red pill is working 👑

#ReclaimD1

39,281 次观看 • 3 个月前

I also made a whole adaptive music system to go alongside this remix! It's meant to replicate the adaptive system that's present in the modern green hill and sky sanctuary stages Full process and behind the scenes are on my channel :)

I also made a whole adaptive music system to go alongside this remix! It's meant to replicate the adaptive system that's present in the modern green hill and sky sanctuary stages Full process and behind the scenes are on my channel :)

Dad’s Last Nerve

30,472 次观看 • 3 个月前

Last week, I received reviews from a journal. 2 of the 3 reviewers pointed out the same issue. 𝑇ℎ𝑒 𝑓𝑜𝑙𝑙𝑜𝑤𝑖𝑛𝑔 𝑝𝑎𝑝𝑒𝑟 𝑖𝑠 𝑚𝑖𝑠𝑠𝑖𝑛𝑔 𝑓𝑟𝑜𝑚 𝑡ℎ𝑒 𝑙𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑟𝑒𝑣𝑖𝑒𝑤. Upon checking, I realized the paper was very relevant. I was surprised how I missed this paper. I re-run the search terms on Google Scholar. The identified paper still went missing. Then I tried searching using ResearchRabbit ResearchRabbit picked the paper. 𝐇𝐞𝐫𝐞 𝐢𝐬 𝐡𝐨𝐰 𝐈 𝐮𝐬𝐞𝐝 𝐑𝐞𝐬𝐞𝐚𝐫𝐜𝐡𝐑𝐚𝐛𝐛𝐢𝐭. 1. I logged into 2. I searched 2-3 papers I already knew 3. ResearchRabbit built a visual map of related papers. 4. Then I explored the map → x-axis shows the publication date → y-axis shows the citation count 5. On each paper in map, I clicked “𝑓𝑖𝑛𝑑 𝑟𝑒𝑙𝑎𝑡𝑒𝑑 𝑝𝑎𝑝𝑒𝑟” 6. This way, each paper becomes a seed 7. With each round, I identified more papers. This way I identified papers that I totally missed before. I saved the papers within the library. I also included the missing papers in my review. You don’t want to miss any relevant papers? Try ResearchRabbit:

Last week, I received reviews from a journal. 2 of the 3 reviewers pointed out the same issue. 𝑇ℎ𝑒 𝑓𝑜𝑙𝑙𝑜𝑤𝑖𝑛𝑔 𝑝𝑎𝑝𝑒𝑟 𝑖𝑠 𝑚𝑖𝑠𝑠𝑖𝑛𝑔 𝑓𝑟𝑜𝑚 𝑡ℎ𝑒 𝑙𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑟𝑒𝑣𝑖𝑒𝑤. Upon checking, I realized the paper was very relevant. I was surprised how I missed this paper. I re-run the search terms on Google Scholar. The identified paper still went missing. Then I tried searching using ResearchRabbit ResearchRabbit picked the paper. 𝐇𝐞𝐫𝐞 𝐢𝐬 𝐡𝐨𝐰 𝐈 𝐮𝐬𝐞𝐝 𝐑𝐞𝐬𝐞𝐚𝐫𝐜𝐡𝐑𝐚𝐛𝐛𝐢𝐭. 1. I logged into 2. I searched 2-3 papers I already knew 3. ResearchRabbit built a visual map of related papers. 4. Then I explored the map → x-axis shows the publication date → y-axis shows the citation count 5. On each paper in map, I clicked “𝑓𝑖𝑛𝑑 𝑟𝑒𝑙𝑎𝑡𝑒𝑑 𝑝𝑎𝑝𝑒𝑟” 6. This way, each paper becomes a seed 7. With each round, I identified more papers. This way I identified papers that I totally missed before. I saved the papers within the library. I also included the missing papers in my review. You don’t want to miss any relevant papers? Try ResearchRabbit:

Faheem Ullah

16,998 次观看 • 7 个月前

I've previously shown how to use stencils using the Amplify Shader Editor. Today, I found out that the Poiyomi shader supports stencils. Here's how you can replicate this effect using that shader, it's gonna be a long thread. (1/6) #VRChat

I've previously shown how to use stencils using the Amplify Shader Editor. Today, I found out that the Poiyomi shader supports stencils. Here's how you can replicate this effect using that shader, it's gonna be a long thread. (1/6) #VRChat

MyroP

32,674 次观看 • 1 年前

American who is a teachers assistant to a college professor is whistleblowing on the tools being used to grade papers He shows they are now using technology that’s so advanced it can actually playback a person typing an entire paper, it can show all their typing, backspacing, deleting, pace, everything when uploaded to Google Docs to be submitted He shows the papers aren’t being graded by the professor if these systems flag them as AI generated or using AI tools. A student would just typically automatically be assigned a fail Now of course a good teacher can also manually review the paper to give a grade but this tool shows how extremely easy it is for a teacher to just have an AI handle things It can also detect if an AI was used to write the paper To get around these new detection methods, AI companies are developing better “humanizers” and auto-typers for students

American who is a teachers assistant to a college professor is whistleblowing on the tools being used to grade papers He shows they are now using technology that’s so advanced it can actually playback a person typing an entire paper, it can show all their typing, backspacing, deleting, pace, everything when uploaded to Google Docs to be submitted He shows the papers aren’t being graded by the professor if these systems flag them as AI generated or using AI tools. A student would just typically automatically be assigned a fail Now of course a good teacher can also manually review the paper to give a grade but this tool shows how extremely easy it is for a teacher to just have an AI handle things It can also detect if an AI was used to write the paper To get around these new detection methods, AI companies are developing better “humanizers” and auto-typers for students

Wall Street Apes

613,593 次观看 • 1 个月前

WOW! I'm so excited about this. OpenAI Developers said Codex was good at Computer Use, but I wasn't prepared for this. For the last two weeks I've been working on a Computer Use skill to work with Linux. And while I had some success, it was a pretty frustrating experience. That is...until the breakthrough. Using accessibility tools, Codex can now control my entire computer, not just the browser. There are limits to this, of course, but what a time to be alive. This Computer Use skill will unlock and entirely new set of automations, all powered by Codex. Demonstration below 👇

WOW! I'm so excited about this. OpenAI Developers said Codex was good at Computer Use, but I wasn't prepared for this. For the last two weeks I've been working on a Computer Use skill to work with Linux. And while I had some success, it was a pretty frustrating experience. That is...until the breakthrough. Using accessibility tools, Codex can now control my entire computer, not just the browser. There are limits to this, of course, but what a time to be alive. This Computer Use skill will unlock and entirely new set of automations, all powered by Codex. Demonstration below 👇

am.will

79,657 次观看 • 4 个月前

Bothered by the anti-war protests that swept the country so quickly, Trump is now echoing talking points that people are paid to protest. His evidence? The organizations behind them move quickly, share PDFs of designs, and use a copier with yellow paper.

Bothered by the anti-war protests that swept the country so quickly, Trump is now echoing talking points that people are paid to protest. His evidence? The organizations behind them move quickly, share PDFs of designs, and use a copier with yellow paper.

BreakThrough News

13,789 次观看 • 7 个月前

Btwww, this is my first time recording myself, so i know there are probably a lot of grammar mistakes. Sorry about that🙏 Quick technical breakdown: - Knowledge Base: Built entirely on top of my obsidian vault using its native graph view - Data Pipeline: reads and caches all my markdown files locally

Btwww, this is my first time recording myself, so i know there are probably a lot of grammar mistakes. Sorry about that🙏 Quick technical breakdown: - Knowledge Base: Built entirely on top of my obsidian vault using its native graph view - Data Pipeline: reads and caches all my markdown files locally

rhmi_fii

102,169 次观看 • 1 个月前

Everyone's talking about vibe coding without looking at code. I was skeptical. I decided to give it a shot on a challenging problem and was blown away by what I could accomplish in 8 hours. I'm not skeptical anymore, but I also do NOT think it kills SaaS Notes: - I tried to replicate some of my favorite features from the Solve-It platform as a jupyter extension - I've tried this many times before, and it didn't work. - I gave my agent specific testing tools that I packaged as skills. I used AI to write the skills. I found the right testing workflow for this Jupyter extension by having AI peruse lots of other extensions and the Jupyter source code. - I had the AI write and maintain a large suite of tests the whole time. I think this was important in keeping the AI on track. - I watched the diffs and the thinking traces as they streamed by. From time to time, I would see something very suspicious like " try ... except: pass" And would stop the AI and tell it to stop this behavior. Then trigger a comprehensive code review using AI. - Most importantly, I don't think this kills SasS at all. Even if I can create software that replicates some of my favorite features, there is an insanely long tail of paper cuts and features I don't want to manage. The models and capabilities are improving so fast that I don't want to constantly tune everything. So I would rather leave that up to people who are focused on that daily and have good taste, with the knowledge that it has been battle tested against many users.

Everyone's talking about vibe coding without looking at code. I was skeptical. I decided to give it a shot on a challenging problem and was blown away by what I could accomplish in 8 hours. I'm not skeptical anymore, but I also do NOT think it kills SaaS Notes: - I tried to replicate some of my favorite features from the Solve-It platform as a jupyter extension - I've tried this many times before, and it didn't work. - I gave my agent specific testing tools that I packaged as skills. I used AI to write the skills. I found the right testing workflow for this Jupyter extension by having AI peruse lots of other extensions and the Jupyter source code. - I had the AI write and maintain a large suite of tests the whole time. I think this was important in keeping the AI on track. - I watched the diffs and the thinking traces as they streamed by. From time to time, I would see something very suspicious like " try ... except: pass" And would stop the AI and tell it to stop this behavior. Then trigger a comprehensive code review using AI. - Most importantly, I don't think this kills SasS at all. Even if I can create software that replicates some of my favorite features, there is an insanely long tail of paper cuts and features I don't want to manage. The models and capabilities are improving so fast that I don't want to constantly tune everything. So I would rather leave that up to people who are focused on that daily and have good taste, with the knowledge that it has been battle tested against many users.

Hamel Husain

48,930 次观看 • 7 个月前

Currently working on a post for next week that I’m VERY excited about but had to stop my work to show you this: My usual workflow for cutting a video involves a rough storyboard on paper to plan out the shots I want to use, etc.—but since I was already working in Vision Pro, I thought I’d change things up this time. So I used the app TouchDesk and turned my table into a big whiteboard. Vision Pro is still a life hack, you can't tell me otherwise.

Currently working on a post for next week that I’m VERY excited about but had to stop my work to show you this: My usual workflow for cutting a video involves a rough storyboard on paper to plan out the shots I want to use, etc.—but since I was already working in Vision Pro, I thought I’d change things up this time. So I used the app TouchDesk and turned my table into a big whiteboard. Vision Pro is still a life hack, you can't tell me otherwise.

Phil Traut ᯅ

17,386 次观看 • 1 年前