正在加载视频...

视频加载失败

返回首页

day 4 of building an OpenCode clone from scratch i have a newfound appreciation for how good this tool is, and how much attention to detail was put into making it. here is what i managed to clone, and problems i've encountered: 1. scrollable autocomplete. mouse click to select,...

codewithantonio's profile picture

Code With Antonio

24,639 subscribers

69,394 次观看 • 5 个月前 •via X (Twitter)

教育科学技术
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

First of its kind? New feature in Ghostty: a web-inspector-style "terminal inspector" targeted at CLI, TUI developers. Built right into the terminal, you can see a live view of terminal state, keyboard events, escape sequences, and much much more. 👻💖 Video tour below. Similar to Firebug with Firefox, I'm hoping this helps usher in a new era of develop-ability for terminal applications by making it much much easier to understand what is going on. When the inspector is not in use, there is no perceivable performance impact (benchmarks show the same). When the inspector is in use, the terminal it is inspecting slows down to about half speed due to the overhead. But this only impacts the terminal being inspected. This is a really early version of the inspector. The data organization is kind of messy, its mostly read-only information right now, and there is a lot more information I want to surface. The next step is making a lot of this data read-write so you can actually modify the terminal live (similar to modifying HTML/CSS live in a web inspector) to trial-and-error some changes. This is just the beginning. 😎 Follow along Ghostty development here:
5:42

First of its kind? New feature in Ghostty: a web-inspector-style "terminal inspector" targeted at CLI, TUI developers. Built right into the terminal, you can see a live view of terminal state, keyboard events, escape sequences, and much much more. 👻💖 Video tour below. Similar to Firebug with Firefox, I'm hoping this helps usher in a new era of develop-ability for terminal applications by making it much much easier to understand what is going on. When the inspector is not in use, there is no perceivable performance impact (benchmarks show the same). When the inspector is in use, the terminal it is inspecting slows down to about half speed due to the overhead. But this only impacts the terminal being inspected. This is a really early version of the inspector. The data organization is kind of messy, its mostly read-only information right now, and there is a lot more information I want to surface. The next step is making a lot of this data read-write so you can actually modify the terminal live (similar to modifying HTML/CSS live in a web inspector) to trial-and-error some changes. This is just the beginning. 😎 Follow along Ghostty development here:

Mitchell Hashimoto

96,262 次观看 • 2 年前

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!
2:57

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

200,950 次观看 • 1 年前

On assisted death for women with terminal anorexia: After a series of committee witnesses have dismissed Chelsea Roff's findings, Dr Naomi Richards says it happens in the AD model for this bill but is a "very minor issue", and "a bit of a red herring", a distraction from "a new mode of dying". "It's like a very sort of minor kind of issue to get focused on. I've seen so much about this in the press and discussed here..." "there is 1 or 2 cases. I mean, this is not something that should be given a huge amount of time because it's a distraction from the fact that really what we're talking about is a new mode of dying" ... "to get fixated on the two people with terminal anorexia who have access to assisted dying in the States is a bit of a red herring, I think."
3:12

On assisted death for women with terminal anorexia: After a series of committee witnesses have dismissed Chelsea Roff's findings, Dr Naomi Richards says it happens in the AD model for this bill but is a "very minor issue", and "a bit of a red herring", a distraction from "a new mode of dying". "It's like a very sort of minor kind of issue to get focused on. I've seen so much about this in the press and discussed here..." "there is 1 or 2 cases. I mean, this is not something that should be given a huge amount of time because it's a distraction from the fact that really what we're talking about is a new mode of dying" ... "to get fixated on the two people with terminal anorexia who have access to assisted dying in the States is a bit of a red herring, I think."

The Other Half

195,843 次观看 • 1 年前

made this in blender and react. still surprising how powerful a tool functional composition is. the ticker is solved with minimal effort, same semantics devs would use on the web. this is a side that is generally ignored in webgl/threejs. canvas3d is thought of in terms of scene primitives, math and shaders. these are all good to know. but i see people all the time trying to use these for solving problems that are inherently of a compositional nature, and fail. imperative javascript and oop lack composition. this is the only thing react adds to threejs (and any other platform it renders to), it allows it to compose.
0:29

made this in blender and react. still surprising how powerful a tool functional composition is. the ticker is solved with minimal effort, same semantics devs would use on the web. this is a side that is generally ignored in webgl/threejs. canvas3d is thought of in terms of scene primitives, math and shaders. these are all good to know. but i see people all the time trying to use these for solving problems that are inherently of a compositional nature, and fail. imperative javascript and oop lack composition. this is the only thing react adds to threejs (and any other platform it renders to), it allows it to compose.

☄︎

30,490 次观看 • 2 年前

Peter Thiel gave a speech in a Hilton in 2010 that holds the keys to unlocking the source of many of America’s most severe problems. Key quote: “The task in this world… where politics has become so broken… is to find a way to escape from it. It’s not a way to fix it.” Palantir is currently tightening its grip around all of our data. Elon Musk is diverting untold billions into a Mars fantasy. All of the anarchist, antidemocratic ideas of the PayPal Mafia and the “Dark Enlightenment”—to use technology as an “escape”—were already well in process 15 years ago. —The internet as “alternate virtual reality” so you don’t have to “constantly convince people.” This is why he funded Satoshi (Bitcoin), MAGA3X (Pizzagate, Q), and pushed Musk to buy Twitter —PayPal (now blockchain/crypto/BTC) was to “overturn the monetary system” —“Escape” now more often referred to as “exit” —“Autonomous countries” now known as the “network state” JD Vance is a full member of the cult of the broligarchs. Unfortunately, this has been a very thorough coup and they have backup. It’s worth really absorbing what the living Antichrist, Peter Thiel, is saying here: “I don't think despair is the only answer. And I don't think, and it's because I don't think politics is the only way to go. And my thinking on this, you know, started to take a turn towards a more optimistic perspective in the mid to late '90s when I got involved in the tech boom in Silicon Valley. I ended up being the co-founder of a company called PayPal where -- and the initial founding vision was that we were going to use technology to change the whole world and basically overturn on the monetary system of the world. And, you know, we can debate on how much it succeeded or how little it succeeded. And there were parts of it that I think have worked, and parts of it were, you know, the jury is still out. But the basic idea was that we could never win an election on getting certain things. Because we were in such a small minority. But maybe you could actually unilaterally change the world without having to constantly convince people and beg people and plead with people who are never going to agree with you through a technological means. And this is where I think technology is this incredible alternative to politics. And, you know, there are a number of different technologies we can outline, but the task in this world where politics has become so broken and so dysfunctional is to find a way to escape from it. It's not a way to fix it. It is a way to escape. And there are, you know, a number of different options. I think the promising one of the 1990s and this last decade has been to escape onto the Internet and to sort of create an alternate virtual reality. Questions, of course, is still how does it intersect with the real world? There are, I think, escaping to outer space is a promise, although I think the space technology is not quite there. So I think that's sort of for the second half of the 21st century. I think we can try to, you know, create autonomous countries on oceans, underwater, all sorts of other spaces. But I think technology is the vehicle for how we should be looking to escape and move beyond politics as we find it today.”
2:09

Peter Thiel gave a speech in a Hilton in 2010 that holds the keys to unlocking the source of many of America’s most severe problems. Key quote: “The task in this world… where politics has become so broken… is to find a way to escape from it. It’s not a way to fix it.” Palantir is currently tightening its grip around all of our data. Elon Musk is diverting untold billions into a Mars fantasy. All of the anarchist, antidemocratic ideas of the PayPal Mafia and the “Dark Enlightenment”—to use technology as an “escape”—were already well in process 15 years ago. —The internet as “alternate virtual reality” so you don’t have to “constantly convince people.” This is why he funded Satoshi (Bitcoin), MAGA3X (Pizzagate, Q), and pushed Musk to buy Twitter —PayPal (now blockchain/crypto/BTC) was to “overturn the monetary system” —“Escape” now more often referred to as “exit” —“Autonomous countries” now known as the “network state” JD Vance is a full member of the cult of the broligarchs. Unfortunately, this has been a very thorough coup and they have backup. It’s worth really absorbing what the living Antichrist, Peter Thiel, is saying here: “I don't think despair is the only answer. And I don't think, and it's because I don't think politics is the only way to go. And my thinking on this, you know, started to take a turn towards a more optimistic perspective in the mid to late '90s when I got involved in the tech boom in Silicon Valley. I ended up being the co-founder of a company called PayPal where -- and the initial founding vision was that we were going to use technology to change the whole world and basically overturn on the monetary system of the world. And, you know, we can debate on how much it succeeded or how little it succeeded. And there were parts of it that I think have worked, and parts of it were, you know, the jury is still out. But the basic idea was that we could never win an election on getting certain things. Because we were in such a small minority. But maybe you could actually unilaterally change the world without having to constantly convince people and beg people and plead with people who are never going to agree with you through a technological means. And this is where I think technology is this incredible alternative to politics. And, you know, there are a number of different technologies we can outline, but the task in this world where politics has become so broken and so dysfunctional is to find a way to escape from it. It's not a way to fix it. It is a way to escape. And there are, you know, a number of different options. I think the promising one of the 1990s and this last decade has been to escape onto the Internet and to sort of create an alternate virtual reality. Questions, of course, is still how does it intersect with the real world? There are, I think, escaping to outer space is a promise, although I think the space technology is not quite there. So I think that's sort of for the second half of the 21st century. I think we can try to, you know, create autonomous countries on oceans, underwater, all sorts of other spaces. But I think technology is the vehicle for how we should be looking to escape and move beyond politics as we find it today.”

Jim Stewartson, Decelerationist 🇨🇦🇺🇦🇺🇸

156,800 次观看 • 1 年前

Imagine an AI application that can type anywhere you can and use the full context of what's on your screen. ​ This is the application we all deserve (at least if you have macOS.) ​ Check out Omnipilot. It's an app that works with every other macOS application and uses Claude Sonet 3.5 in the background—it also supports Gemini and GPT-4o. ​ ​ Here is the idea: ​ You can use the tool to ask questions about anything on your screen. Or you can use it to autocomplete the text you are typing. You don't need to copy and paste anymore or waste your time providing context to a model. ​ It sees what you see. It works right where you are. ​ That's pretty cool. ​ Here are a couple of cool examples: ​ • Use it to reply to an email • Use it in the terminal to autocomplete a command • Use it to finish a document • Use to send a message on Slack ​ AI at the system level is bonkers. You can read a ton more on their Product Hunt launch page: ​ ​ Thanks to the Omnipilot team for collaborating with me on this post!
0:29

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

Santiago

72,306 次观看 • 2 年前

Arteta on his role to re-energise the Arsenal team. 💪 “Certainly, when you lose a game, you have a lot of feelings because, especially, this group of players are so competitive and they seek for excellence and when you don't reach it, you ask yourself questions, and we did that. “But I think my role there as well is to bring optimism and reality about where we are, and yeah, our club has a long history. And to find a moment where, in February, we're in the position that we are, is very difficult to find. So guys, we are doing so many things so well, and let's focus mainly on that. And for sure, we want to improve, we want to be better in every area, but with that sense as well of self-confidence and conviction that we are in the right path. Anyone need to lift Arteta? “No, in these moments, no. Normally, I'm the opposite and when we are doing so well, I'm there with a stick to say, 'This is not good enough,' 'This is not good enough.' The other day, no, because I know how much they wanted the amount of games and the demands that we put on those players every day. “In those moments, they need to understand and feel that we are right behind them. I'm mainly responsible for that and they keep playing with that freedom, with that enjoyment, as I discussed the other day, and I make sure that that journey is beautiful because what is ahead is great and everybody has to be part of that but in a good sense and with good humor and with good optimism and looking forward to it.”
1:58

Arteta on his role to re-energise the Arsenal team. 💪 “Certainly, when you lose a game, you have a lot of feelings because, especially, this group of players are so competitive and they seek for excellence and when you don't reach it, you ask yourself questions, and we did that. “But I think my role there as well is to bring optimism and reality about where we are, and yeah, our club has a long history. And to find a moment where, in February, we're in the position that we are, is very difficult to find. So guys, we are doing so many things so well, and let's focus mainly on that. And for sure, we want to improve, we want to be better in every area, but with that sense as well of self-confidence and conviction that we are in the right path. Anyone need to lift Arteta? “No, in these moments, no. Normally, I'm the opposite and when we are doing so well, I'm there with a stick to say, 'This is not good enough,' 'This is not good enough.' The other day, no, because I know how much they wanted the amount of games and the demands that we put on those players every day. “In those moments, they need to understand and feel that we are right behind them. I'm mainly responsible for that and they keep playing with that freedom, with that enjoyment, as I discussed the other day, and I make sure that that journey is beautiful because what is ahead is great and everybody has to be part of that but in a good sense and with good humor and with good optimism and looking forward to it.”

Connor Humm

17,767 次观看 • 6 个月前

Jake, who built a $50K/month alarm app in 4 months, says the most valuable skill right now isn't building it's... "Focus on top of funnel only. That is the most valuable skill right now is marketing. There's so many people that can build an app and it's so easy with AI, but there's not so many people that know how to market and know how to get views." "If nobody knows about your app, it doesn't exist. You can build as many features as you want." "Building doesn't really matter so much. You got to build a good product, of course. But getting views is more of the unknown."
0:27

Jake, who built a $50K/month alarm app in 4 months, says the most valuable skill right now isn't building it's... "Focus on top of funnel only. That is the most valuable skill right now is marketing. There's so many people that can build an app and it's so easy with AI, but there's not so many people that know how to market and know how to get views." "If nobody knows about your app, it doesn't exist. You can build as many features as you want." "Building doesn't really matter so much. You got to build a good product, of course. But getting views is more of the unknown."

Starter Story

331,916 次观看 • 1 个月前

A little bit more on my Novel editor. One of the things I loath about word processors is that they are so unaware of how prose is structured. They treat the line as the most atomic unit of text. But writers think in words, sentences, and paragraphs. Never lines. The editor I am working on has navigation tools for word, sentence, paragraph, and scene. You can navigate and move content at each level. All from the keyboard with some intuitive hotkeys. A pointing device like trackpad or mouse engages the part of your brain that processes spatial input. That's not where you want to be when writing. It can take you out of your flow state. And it is physically quite slow because your hands must move away from the keyboard. So I'm rethinking editing with the keyboard. It's not hard to learn, and it makes editing faster. I haven't been using it long and already I'm barely reaching for the trackpad. Follow me to be the first to try this out. #WritingCommunity
0:49

A little bit more on my Novel editor. One of the things I loath about word processors is that they are so unaware of how prose is structured. They treat the line as the most atomic unit of text. But writers think in words, sentences, and paragraphs. Never lines. The editor I am working on has navigation tools for word, sentence, paragraph, and scene. You can navigate and move content at each level. All from the keyboard with some intuitive hotkeys. A pointing device like trackpad or mouse engages the part of your brain that processes spatial input. That's not where you want to be when writing. It can take you out of your flow state. And it is physically quite slow because your hands must move away from the keyboard. So I'm rethinking editing with the keyboard. It's not hard to learn, and it makes editing faster. I haven't been using it long and already I'm barely reaching for the trackpad. Follow me to be the first to try this out. #WritingCommunity

Will McGugan

16,027 次观看 • 1 个月前

I hear so often from the Dommes I work with that they struggle with people online fetichizing them and simply seeing them for how sexy and beautiful they are. They project their fantasies and their desires onto you. That stops immediately once you move the attention from you to them. From 'look at me' to 'I see you'. What does that look like? When you create content, think of them and what this scene or that narrative is evoking. What will they learn from you? What they want is not to passively watch how sexy you are, but for you to train them, to give them instructions, to teach them, to guide them, to be in charge, to command them. This is not being an object but the main subject. The Authority figure. How is your content already doing that. The sexy photos can still be there, they are important to already capture des attention. But what you do with that attention once you have it, is where the power dynamic is established. Positioning yourself as more than a stunning Goddess, but actually a woman who has a voice, opinions, perspective, a philosophy, a way to doing things, teaching them what you like, how you like it, why you like it, already makes them want to be that for you. You hold the attention, you hold the power, so you direct it. And for that, you want them to know you get them and you know what lives within them... that creates the desire for you to be the one exposing it. You instantly build trust. Not because you demanded it, but because you earned it: you showed them you know what you are doing. You have experience, you understand them. They are not told to come see you, they are seduced into it. They desire it. And they will work for it. This will attract better clients (real subs) and instead of you trying to get their attention, they will work to earn yours. If you want to learn more about power dynamics, building a brand as a Pro or the psychology behind BDSM, you can now access all my trainings and classes in one place for a fraction of the cost of The Dominatrix Academy. And you can reinvest the total amount towards the Program. Message me [SECRET] for the details. This offer is not available on my website.
0:51

I hear so often from the Dommes I work with that they struggle with people online fetichizing them and simply seeing them for how sexy and beautiful they are. They project their fantasies and their desires onto you. That stops immediately once you move the attention from you to them. From 'look at me' to 'I see you'. What does that look like? When you create content, think of them and what this scene or that narrative is evoking. What will they learn from you? What they want is not to passively watch how sexy you are, but for you to train them, to give them instructions, to teach them, to guide them, to be in charge, to command them. This is not being an object but the main subject. The Authority figure. How is your content already doing that. The sexy photos can still be there, they are important to already capture des attention. But what you do with that attention once you have it, is where the power dynamic is established. Positioning yourself as more than a stunning Goddess, but actually a woman who has a voice, opinions, perspective, a philosophy, a way to doing things, teaching them what you like, how you like it, why you like it, already makes them want to be that for you. You hold the attention, you hold the power, so you direct it. And for that, you want them to know you get them and you know what lives within them... that creates the desire for you to be the one exposing it. You instantly build trust. Not because you demanded it, but because you earned it: you showed them you know what you are doing. You have experience, you understand them. They are not told to come see you, they are seduced into it. They desire it. And they will work for it. This will attract better clients (real subs) and instead of you trying to get their attention, they will work to earn yours. If you want to learn more about power dynamics, building a brand as a Pro or the psychology behind BDSM, you can now access all my trainings and classes in one place for a fraction of the cost of The Dominatrix Academy. And you can reinvest the total amount towards the Program. Message me [SECRET] for the details. This offer is not available on my website.

Ms. Malissia

16,120 次观看 • 3 个月前

Most AI tools today are just command-takers. You type, it responds. You click, it executes. There's truly no learning, no memory, no adaptation. You're still doing most of the work. Which is why Miles by Avo on Solana would make so much sense if built well. From what I understand so far, miles learns about you over time, adapts to how you operate, and figures out the tools you struggle to navigate on your own. Less clicking, more conversation, the more you use it, the better it gets at working with you, not just for you. That shift from command-follower to learning companion is bigger than it sounds. It's the difference between a tool and an agent that actually knows you. The second one is Agent Grid and this one is for builders and power users. But as I mentioned in this video, I'm still studying the Agent Grid. I'd come talk about it once I learn properly about it. Souren just keeps shipping!
1:28

Most AI tools today are just command-takers. You type, it responds. You click, it executes. There's truly no learning, no memory, no adaptation. You're still doing most of the work. Which is why Miles by Avo on Solana would make so much sense if built well. From what I understand so far, miles learns about you over time, adapts to how you operate, and figures out the tools you struggle to navigate on your own. Less clicking, more conversation, the more you use it, the better it gets at working with you, not just for you. That shift from command-follower to learning companion is bigger than it sounds. It's the difference between a tool and an agent that actually knows you. The second one is Agent Grid and this one is for builders and power users. But as I mentioned in this video, I'm still studying the Agent Grid. I'd come talk about it once I learn properly about it. Souren just keeps shipping!

Sir Khaycee

20,419 次观看 • 4 个月前

I've been playing with a feature for my prose editor, I call "ghost cut". Y'all know how to cut and paste. You hit ctrl+x, the text disappears and goes into the clipboard. Then you move the caret and ctrl+v to paste it into a new location. You've done that a bazillion times, I bet. An annoyance I have with this is that as soon as you cut, the text reflows—and you have to reorient yourself in the "page". The solution I'm playing with is to ghost the text that was just cut. It only disappears from view once you paste it. I'm kinda liking it so far. But there is more testing to be done. Does anyone know of any precedence for this? I've not seen this in any editor or word processor.
0:51

I've been playing with a feature for my prose editor, I call "ghost cut". Y'all know how to cut and paste. You hit ctrl+x, the text disappears and goes into the clipboard. Then you move the caret and ctrl+v to paste it into a new location. You've done that a bazillion times, I bet. An annoyance I have with this is that as soon as you cut, the text reflows—and you have to reorient yourself in the "page". The solution I'm playing with is to ghost the text that was just cut. It only disappears from view once you paste it. I'm kinda liking it so far. But there is more testing to be done. Does anyone know of any precedence for this? I've not seen this in any editor or word processor.

Will McGugan

20,226 次观看 • 1 个月前

Right now, I have a few dozen tools to automate my life. Every single thing that I do more than once every week is now a tool: either a Claude Code skill, a scheduled workflow, or an application. • I spend the time doing this once. • I schedule it. • I forget about it (or at least, try to) CREAO is one of the platforms I've used extensively for building some of these automations. They are partnering with me on this post. They are one of the only platforms where you can go from a conversation to a scheduled agent that quickly. This is how it works: 1. You describe the problem you want to solve 2. CREAO's agent builds the logic and executes it 3. You can iterate with the agent to improve the solution 4. When you are done, you turn that solution into a mini app 5. You can schedule that app to run any time you need it Something important: These agents are deterministic. They don't use an LLM to generate answers, so they will always return the same output given the same input. This is critical: when you're automating something that runs every Monday at 9 am, you need it to return the same result every time, not a "creative" answer.
5:00

Right now, I have a few dozen tools to automate my life. Every single thing that I do more than once every week is now a tool: either a Claude Code skill, a scheduled workflow, or an application. • I spend the time doing this once. • I schedule it. • I forget about it (or at least, try to) CREAO is one of the platforms I've used extensively for building some of these automations. They are partnering with me on this post. They are one of the only platforms where you can go from a conversation to a scheduled agent that quickly. This is how it works: 1. You describe the problem you want to solve 2. CREAO's agent builds the logic and executes it 3. You can iterate with the agent to improve the solution 4. When you are done, you turn that solution into a mini app 5. You can schedule that app to run any time you need it Something important: These agents are deterministic. They don't use an LLM to generate answers, so they will always return the same output given the same input. This is critical: when you're automating something that runs every Monday at 9 am, you need it to return the same result every time, not a "creative" answer.

Santiago

13,712 次观看 • 4 个月前

OpenTUI Keymap is a host agnostic key/cmd engine for DOM like apps. It allows extreme customisation of a generic core, from key stroke syntax parsing to to command resolution and dispatch behaviour. It composes layers of bindings and commands into a single adaptive dispatch model. Demo link in the replies. There are many such systems, most of which stop at the key binding part. Apps often are expected to implement their own command layer on top of these. This disconnects the bindings from the actual command registry. Looking for a proper solution usable in OpenCode I couldn't find anything that fulfilled the need of being extremely extensible to allow plugins to fully control key mapping and command behaviour. I wanted it to always be able to know exactly which keys and commands are reachable at any point in time, no matter from where and how the mappings are manipulated. The main driver was enabling a which-key like plugin and vim like bindings in a mostly declarative way. While any other plugin could extend the keymap even further with a custom config syntax for key strokes for example. So addons for it are mostly composable and it comes with a variety of addons providing common behaviour. It can also power other discovery features directly from live state. Help views, command palettes and graph/debug UIs can all ask the engine what is active, reachable, shadowed, pending, or dispatchable instead of rebuilding that knowledge separately. The core is intentionally very much generic: hosts adapt focus, hierarchy, input events, and lifecycle, while addons extend parsing, tokens, sequence patterns, command metadata, resolvers, interceptors, and event matching. The result is a keymap that plugins can compose with rather than work around. This could all be built directly into OpenCode and just be app specific. Working on OpenTUI though I want applications to have an out-of-the-box solution to build keyboard-first apps easily. Well, at least agents can. It is extremely over-engineered. And I love it. I hope some of you will too.
1:27

OpenTUI Keymap is a host agnostic key/cmd engine for DOM like apps. It allows extreme customisation of a generic core, from key stroke syntax parsing to to command resolution and dispatch behaviour. It composes layers of bindings and commands into a single adaptive dispatch model. Demo link in the replies. There are many such systems, most of which stop at the key binding part. Apps often are expected to implement their own command layer on top of these. This disconnects the bindings from the actual command registry. Looking for a proper solution usable in OpenCode I couldn't find anything that fulfilled the need of being extremely extensible to allow plugins to fully control key mapping and command behaviour. I wanted it to always be able to know exactly which keys and commands are reachable at any point in time, no matter from where and how the mappings are manipulated. The main driver was enabling a which-key like plugin and vim like bindings in a mostly declarative way. While any other plugin could extend the keymap even further with a custom config syntax for key strokes for example. So addons for it are mostly composable and it comes with a variety of addons providing common behaviour. It can also power other discovery features directly from live state. Help views, command palettes and graph/debug UIs can all ask the engine what is active, reachable, shadowed, pending, or dispatchable instead of rebuilding that knowledge separately. The core is intentionally very much generic: hosts adapt focus, hierarchy, input events, and lifecycle, while addons extend parsing, tokens, sequence patterns, command metadata, resolvers, interceptors, and event matching. The result is a keymap that plugins can compose with rather than work around. This could all be built directly into OpenCode and just be app specific. Working on OpenTUI though I want applications to have an out-of-the-box solution to build keyboard-first apps easily. Well, at least agents can. It is extremely over-engineered. And I love it. I hope some of you will too.

kmdr

91,090 次观看 • 3 个月前

The END of an ERA Well over a Quarter of a Million Users Built on the Support of this Community Squatingdog for Fortnite's time is finally up This is an emotional post to share. I've been a part of this community since Fortnite's inception. I've created guides, cheatsheets, and concepts since the very beginning by helping players maximize their battle-passes. Along the way you've supported me with my support-a-creator and every dime of that went back to you in a free app which has evolved from the mere cheat sheet. I put in ads and Twitch support to cover the cost of the servers and was able to maintain them up until now. However it is time to put the app to rest. The reason for this comes two fold, one is that Fortnite themselves has engulfed every aspect of what made this app a valuable tool to a player. Secondly, I am building up a company from the ground up to maximize the potential of Fortnite Creative. Both of these two hand in hand make updating this app more and more difficult to maintain. My time is becoming scarce with these new intitatives, also with a child on the way, and becoming a home owner very soon it is very clear that it is time to shut down or sell my app. (if you are interested let me know) This isn't goodbye by any means. I am proud of what I created and am only more proud of what to show you next! A lot has been brewing behind the scenes. Stay tuned, and much love!
0:50

The END of an ERA Well over a Quarter of a Million Users Built on the Support of this Community Squatingdog for Fortnite's time is finally up This is an emotional post to share. I've been a part of this community since Fortnite's inception. I've created guides, cheatsheets, and concepts since the very beginning by helping players maximize their battle-passes. Along the way you've supported me with my support-a-creator and every dime of that went back to you in a free app which has evolved from the mere cheat sheet. I put in ads and Twitch support to cover the cost of the servers and was able to maintain them up until now. However it is time to put the app to rest. The reason for this comes two fold, one is that Fortnite themselves has engulfed every aspect of what made this app a valuable tool to a player. Secondly, I am building up a company from the ground up to maximize the potential of Fortnite Creative. Both of these two hand in hand make updating this app more and more difficult to maintain. My time is becoming scarce with these new intitatives, also with a child on the way, and becoming a home owner very soon it is very clear that it is time to shut down or sell my app. (if you are interested let me know) This isn't goodbye by any means. I am proud of what I created and am only more proud of what to show you next! A lot has been brewing behind the scenes. Stay tuned, and much love!

Squatingdog

66,926 次观看 • 2 年前

WOW. Marcelo Bielsa is 70 years of age, and his parting message to Uruguay carries a lesson every coach should sit with. No group is the same. No individual is the same. Nobody. Bielsa admits he has never tried to be the “friendly” coach. He values order, discipline, seriousness, obsession. That has made him one of the most respected minds in football. But even Bielsa seems to accept something powerful here: That approach does not work for every player. It does not work in every environment. And knowledge alone is never enough. As a coach, you have to find a way to connect. Quote us on this: “You can have all the knowledge in the world, but it is absolutely useless if the people playing don’t like you. Player management and people management might not be on coaching courses, but don’t be kidded by associations. It is the most important quality a coach can have.” Football is about tactics, detail, preparation and standards. But above all, it is about people. So many coaches out there fail to grasp this, they think they can shout their way to development or success, and this day and age you simply can't.
1:24

WOW. Marcelo Bielsa is 70 years of age, and his parting message to Uruguay carries a lesson every coach should sit with. No group is the same. No individual is the same. Nobody. Bielsa admits he has never tried to be the “friendly” coach. He values order, discipline, seriousness, obsession. That has made him one of the most respected minds in football. But even Bielsa seems to accept something powerful here: That approach does not work for every player. It does not work in every environment. And knowledge alone is never enough. As a coach, you have to find a way to connect. Quote us on this: “You can have all the knowledge in the world, but it is absolutely useless if the people playing don’t like you. Player management and people management might not be on coaching courses, but don’t be kidded by associations. It is the most important quality a coach can have.” Football is about tactics, detail, preparation and standards. But above all, it is about people. So many coaches out there fail to grasp this, they think they can shout their way to development or success, and this day and age you simply can't.

Keepitonthedeck

119,101 次观看 • 1 个月前

American Surgeon shows the actual letter from UnitedHealthcare DENYING a patient in emergency condition from receiving care “This is a woman who was in the emergency room with pulmonary embolisms” “I think we all knew this would happen. I had another patient come in and share with me that UnitedHealthcare denied her inpatient's day. So this is a patient who had shortness of breath and some chest pain, and she just knew that something wasn't right in her body. She had a family history of blood clots and she'd had a deep flap surgery a couple of weeks ago. She went to the hospital and they saw her and they found that she had a life threatening condition known as pulmonary embolisms. So she was admitted to the hospital and taken care of really well by the doctors there. And they ordered all the right things. After a couple of days, she was discharged. She got a letter from UnitedHealthcare explaining that they didn't agree with the level of her care and that they would not cover it. So I'm gonna share some of the language of that letter with you, and I want you to know that my patient that we talked about previously who had her surgery denied had almost exactly the same letter shared. So there's some troubling things in this letter. I think this term is really interesting. United is saying they reviewed the request for inpatient admission. So let's all just pause and consider that. This is a woman who was in the emergency room with pulmonary embolisms, and the doctor wasn't really requesting anything. They were saying this patient needs to be in the hospital. But an insurance company sees this as a request, and that's part of this prior auth environment that we're living in. So I think it's important as patients and as physicians to just acknowledge that this is our reality now. Someone can think that there's a good medical decision for you and can write orders and wanna do the right thing for you, but your insurance company is seeing that as a request and deciding whether or not they wanna do it. One of the criteria that this insurance company used to decide whether or not to accept or deny this request was whether it's medically necessary. And it's so interesting that we're letting insurance companies and the doctors who work for insurance companies determine what's medically necessary and not just the doctor in front of the patient in the emergency room. So this is a really bold statement from UnitedHealthcare for my patient. They say you did not have to be admitted as an inpatient to the hospital for this care. I think we all need to just reflect on that. An insurance company is telling a patient and her doctor that they disagree with the plan of care to keep that patient safe. I know that this is boiling down to whether it's an inpatient admission or an observation admission, and that's really about money. But what I wanna point out to you is they're making medical decisions. This insurance company is actually weighing in and disagreeing with a doctor who made a medical decision to admit this patient for her safety. So this specific sentence, when a doctor or facility treats a patient above the recommended level of care, we cannot cover it. What the heck? That's what we do. We go above and beyond as physicians. It's clear that insurance companies don't, and they're actually saying it here.”
2:35

American Surgeon shows the actual letter from UnitedHealthcare DENYING a patient in emergency condition from receiving care “This is a woman who was in the emergency room with pulmonary embolisms” “I think we all knew this would happen. I had another patient come in and share with me that UnitedHealthcare denied her inpatient's day. So this is a patient who had shortness of breath and some chest pain, and she just knew that something wasn't right in her body. She had a family history of blood clots and she'd had a deep flap surgery a couple of weeks ago. She went to the hospital and they saw her and they found that she had a life threatening condition known as pulmonary embolisms. So she was admitted to the hospital and taken care of really well by the doctors there. And they ordered all the right things. After a couple of days, she was discharged. She got a letter from UnitedHealthcare explaining that they didn't agree with the level of her care and that they would not cover it. So I'm gonna share some of the language of that letter with you, and I want you to know that my patient that we talked about previously who had her surgery denied had almost exactly the same letter shared. So there's some troubling things in this letter. I think this term is really interesting. United is saying they reviewed the request for inpatient admission. So let's all just pause and consider that. This is a woman who was in the emergency room with pulmonary embolisms, and the doctor wasn't really requesting anything. They were saying this patient needs to be in the hospital. But an insurance company sees this as a request, and that's part of this prior auth environment that we're living in. So I think it's important as patients and as physicians to just acknowledge that this is our reality now. Someone can think that there's a good medical decision for you and can write orders and wanna do the right thing for you, but your insurance company is seeing that as a request and deciding whether or not they wanna do it. One of the criteria that this insurance company used to decide whether or not to accept or deny this request was whether it's medically necessary. And it's so interesting that we're letting insurance companies and the doctors who work for insurance companies determine what's medically necessary and not just the doctor in front of the patient in the emergency room. So this is a really bold statement from UnitedHealthcare for my patient. They say you did not have to be admitted as an inpatient to the hospital for this care. I think we all need to just reflect on that. An insurance company is telling a patient and her doctor that they disagree with the plan of care to keep that patient safe. I know that this is boiling down to whether it's an inpatient admission or an observation admission, and that's really about money. But what I wanna point out to you is they're making medical decisions. This insurance company is actually weighing in and disagreeing with a doctor who made a medical decision to admit this patient for her safety. So this specific sentence, when a doctor or facility treats a patient above the recommended level of care, we cannot cover it. What the heck? That's what we do. We go above and beyond as physicians. It's clear that insurance companies don't, and they're actually saying it here.”

Wall Street Apes

115,712 次观看 • 1 年前

😱😱🚨🚨🚨 Popular Youtube Doctor / Influencer, Dr Boz makes a dramatic U-Turn on the experimental gene therapy. Highlights All right, so this was the other part that bothered me. It bothered me from the beginning, but it really makes me nervous once you see what this I had heard whisperings about this, but I didn't believe it. I did not believe it. so this bothered me from the beginning, though, that they kept using the word vaccine when it was not like a normal vaccine. This is a messenger RNA. this is a strand of single DNA, or rna that you make DNA from, so that you're teaching the body about how to respond to this by impacting your dna. So it shouldn't have been called vaccines. It should have been called gene therapy product, because it was really changing the gene. The problem with what they were playing with is there is no off switch for this. In a vaccination, your immunity rises and then it falls and your body's done with what they were playing with. There's no mechanism built into our bodies that has the ability to turn it off. Like, if you take that messenger, that DNA, you have a messenger RNA. Now you're making a protein. Well, how do you stop making a protein once this turns it on? ..... Some batches were contaminated with double stranded rna. The double stranded DNA has a high potential to trigger immune inflammatory reactions such as myocarditis. So here it gets a little bit. This is where it really bothers me. So you say, well, I don't know much about these vaccinations. Is that like a normal thing to find in your vaccination with an mrna is you're going to have some double stranded things, they say, each batch variability further complicated in recent findings of DNA contamination. Again, DNA contamination. First of all, what the hell is DNA doing in a vaccination that is supposed to be for the protein production to fight off this virus? but in the analysis of multiple vials high levels of DNA contamination in both a monovalent and bivalent vaccines in orders of magnitude higher than the limitations. What they found was an enormous amount of DNA particles in the rna that I injected into me, into my kids, into my patients. so how does such dangerous large scale contamination escape the scrutiny of the public health officials? And were the manufacturers aware of all of this excess dna that was found inside these vaccinations? Oh yeah, this is the part that I wanted to say. so when you have foreign dna in your human genome, it disrupts the existing natural genetic sequence. It also carries a further risk of disease, including cancer. I mean, DNA in your body, very dangerous, just like CRISPR, except it's random chance of what the heck's in there? Because it's a contaminant. It's not intended to be in there. What's it doing in there? .... There is an 803 increase in autoimmune disorders when people had these vaccinations. And it goes on to say, we not only know that, we know that as you look at some of the images from people who have autopsies from death due to myocarditis, I wonder if this is. Here we go. ... This spike proteins are found in the cells of human heart. Cells with spike proteins inside the muscles of these patients. Again, spike proteins are not supposed to be inside us at all. The people who had Covid didn't have spike proteins found in their cardiac tissues. The people who had the vaccinations, the ones who had this messenger rna that made a protein, and then they made the protein and didn't have the off button, well, they're now found at autopsy in the cells of cardiac tissues. And here are the. I mean, that sounds ridiculous. That sounds like something I wouldn't even believe until you start looking at the autopsies and wondering. .... they were using some of the people who started in the placebo line, but ended up with the vaccination in the data for the placebo. So they got the vaccination, they had a significant adverse effect. But they're being counted in the people who didn't get the vaccination because that's where they started. They didn't fix that. So you don't have to be a statistician to understand what I'm trying to say, which is they played games to have this bias towards the favorability of the vaccination. ..... 52,000 vaccinations would be needed in order to prevent one Covid-19 death. Now they go through talking about all this, how this number needed to vaccinate. They are taking a conservative approach to this. So as you do the math, they're rounding in a way to be conservative, giving the benefit of the doubt. and it's saying this exact injection, it is estimated that about two lives could be saved for every 100,000 injections. and then they go to say, but now we see that we have 27 deaths per 100,000 in the same batch of injections that were happening because of adverse events. So you're going to save two lives, but you are going to have 27 deaths as a result of the significant adverse effects. And yet this was not reported. There were nearly 14 times more deaths caused by the modified mrna injections. .... They recommended it in pregnancy when they knew that absolutely not one single subject in the trial was pregnant. I think that's just egregious. .... And then what was my part in it? How could have I been a little more? Again, I had all of my kids vaccinated. I had all of the people I loved vaccinated. And when you look back and say, dang, look at what it did to especially the kids. anyway, I say that to you, to say, this information is out there. I don't know how long this report will be there. I want to do my part in at least spreading the information that's in this report, because, holy mackerel, did a lot of work go into that report.
4:38

😱😱🚨🚨🚨 Popular Youtube Doctor / Influencer, Dr Boz makes a dramatic U-Turn on the experimental gene therapy. Highlights All right, so this was the other part that bothered me. It bothered me from the beginning, but it really makes me nervous once you see what this I had heard whisperings about this, but I didn't believe it. I did not believe it. so this bothered me from the beginning, though, that they kept using the word vaccine when it was not like a normal vaccine. This is a messenger RNA. this is a strand of single DNA, or rna that you make DNA from, so that you're teaching the body about how to respond to this by impacting your dna. So it shouldn't have been called vaccines. It should have been called gene therapy product, because it was really changing the gene. The problem with what they were playing with is there is no off switch for this. In a vaccination, your immunity rises and then it falls and your body's done with what they were playing with. There's no mechanism built into our bodies that has the ability to turn it off. Like, if you take that messenger, that DNA, you have a messenger RNA. Now you're making a protein. Well, how do you stop making a protein once this turns it on? ..... Some batches were contaminated with double stranded rna. The double stranded DNA has a high potential to trigger immune inflammatory reactions such as myocarditis. So here it gets a little bit. This is where it really bothers me. So you say, well, I don't know much about these vaccinations. Is that like a normal thing to find in your vaccination with an mrna is you're going to have some double stranded things, they say, each batch variability further complicated in recent findings of DNA contamination. Again, DNA contamination. First of all, what the hell is DNA doing in a vaccination that is supposed to be for the protein production to fight off this virus? but in the analysis of multiple vials high levels of DNA contamination in both a monovalent and bivalent vaccines in orders of magnitude higher than the limitations. What they found was an enormous amount of DNA particles in the rna that I injected into me, into my kids, into my patients. so how does such dangerous large scale contamination escape the scrutiny of the public health officials? And were the manufacturers aware of all of this excess dna that was found inside these vaccinations? Oh yeah, this is the part that I wanted to say. so when you have foreign dna in your human genome, it disrupts the existing natural genetic sequence. It also carries a further risk of disease, including cancer. I mean, DNA in your body, very dangerous, just like CRISPR, except it's random chance of what the heck's in there? Because it's a contaminant. It's not intended to be in there. What's it doing in there? .... There is an 803 increase in autoimmune disorders when people had these vaccinations. And it goes on to say, we not only know that, we know that as you look at some of the images from people who have autopsies from death due to myocarditis, I wonder if this is. Here we go. ... This spike proteins are found in the cells of human heart. Cells with spike proteins inside the muscles of these patients. Again, spike proteins are not supposed to be inside us at all. The people who had Covid didn't have spike proteins found in their cardiac tissues. The people who had the vaccinations, the ones who had this messenger rna that made a protein, and then they made the protein and didn't have the off button, well, they're now found at autopsy in the cells of cardiac tissues. And here are the. I mean, that sounds ridiculous. That sounds like something I wouldn't even believe until you start looking at the autopsies and wondering. .... they were using some of the people who started in the placebo line, but ended up with the vaccination in the data for the placebo. So they got the vaccination, they had a significant adverse effect. But they're being counted in the people who didn't get the vaccination because that's where they started. They didn't fix that. So you don't have to be a statistician to understand what I'm trying to say, which is they played games to have this bias towards the favorability of the vaccination. ..... 52,000 vaccinations would be needed in order to prevent one Covid-19 death. Now they go through talking about all this, how this number needed to vaccinate. They are taking a conservative approach to this. So as you do the math, they're rounding in a way to be conservative, giving the benefit of the doubt. and it's saying this exact injection, it is estimated that about two lives could be saved for every 100,000 injections. and then they go to say, but now we see that we have 27 deaths per 100,000 in the same batch of injections that were happening because of adverse events. So you're going to save two lives, but you are going to have 27 deaths as a result of the significant adverse effects. And yet this was not reported. There were nearly 14 times more deaths caused by the modified mrna injections. .... They recommended it in pregnancy when they knew that absolutely not one single subject in the trial was pregnant. I think that's just egregious. .... And then what was my part in it? How could have I been a little more? Again, I had all of my kids vaccinated. I had all of the people I loved vaccinated. And when you look back and say, dang, look at what it did to especially the kids. anyway, I say that to you, to say, this information is out there. I don't know how long this report will be there. I want to do my part in at least spreading the information that's in this report, because, holy mackerel, did a lot of work go into that report.

aussie17

440,071 次观看 • 2 年前

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)
1:18

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

Ian Nuttall

194,949 次观看 • 1 年前