Загрузка видео...

Не удалось загрузить видео

На главную

Codex, Claude Code, and Cursor are all great tools. They're also much more different than you think. I did a comparison of the three, but not in the usual way. I went deep on how they differ philosophically.

theo's profile picture

Theo - t3.gg

378,278 subscribers

247,448 просмотров • 3 месяцев назад •via X (Twitter)

ИскусствоОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

🚨 Vice President JD VANCE just dropped this on CHINA: "Say what you will about them. They are not the sort of nation that shoots at commercial shipping because they're not getting their way in an international dispute." "They are in that way, I think willing to be a little bit more responsible." "Again, I'm not saying they're doing everything that we've asked them to do. But I think that the PRC has been much more responsible, certainly than the Iranians, and much more responsible than a couple of other nations as well."
1:05

🚨 Vice President JD VANCE just dropped this on CHINA: "Say what you will about them. They are not the sort of nation that shoots at commercial shipping because they're not getting their way in an international dispute." "They are in that way, I think willing to be a little bit more responsible." "Again, I'm not saying they're doing everything that we've asked them to do. But I think that the PRC has been much more responsible, certainly than the Iranians, and much more responsible than a couple of other nations as well."

Eric Daugherty

76,222 просмотров • 9 дней назад

Is Claude Code Better Than Cursor? This video is a crystal clear explanation on what makes Claude Code different than Cursor, Codex and Windsurf. A classic whiteboard conversation! Next time he's on the pod (soon) he's going to build an app from scratch that will blow your mind. TIMESTAMPS: 00:00 Intro to Claude Code 00:28 Why Claude Code Is Best 02:38 Comparing Cursor, Windsurf & Claude Code 07:41 Using Claude Code with Other IDEs 12:41 Future of AI Coding Tools & Claude’s SDK 19:58 Integrating Codex with Chat GPT 21:14 Best AI Code Review Tools (Devon, CodeRabbit 26:49 Building an App with Claude Code (Step-by-Step) 35:32 Future Plans
37:07

Is Claude Code Better Than Cursor? This video is a crystal clear explanation on what makes Claude Code different than Cursor, Codex and Windsurf. A classic whiteboard conversation! Next time he's on the pod (soon) he's going to build an app from scratch that will blow your mind. TIMESTAMPS: 00:00 Intro to Claude Code 00:28 Why Claude Code Is Best 02:38 Comparing Cursor, Windsurf & Claude Code 07:41 Using Claude Code with Other IDEs 12:41 Future of AI Coding Tools & Claude’s SDK 19:58 Integrating Codex with Chat GPT 21:14 Best AI Code Review Tools (Devon, CodeRabbit 26:49 Building an App with Claude Code (Step-by-Step) 35:32 Future Plans

Riley Brown

115,665 просмотров • 1 год назад

Cursor, WindSurf, and Copilot suck with Jupyter notebooks. They are great when you are writing regular code, but notebooks are a different monster. Vincent is an extension fine-tuned to work with notebooks. 10x better than the other tools! Here is a quick video:
4:20

Cursor, WindSurf, and Copilot suck with Jupyter notebooks. They are great when you are writing regular code, but notebooks are a different monster. Vincent is an extension fine-tuned to work with notebooks. 10x better than the other tools! Here is a quick video:

Santiago

148,184 просмотров • 1 год назад

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

195,173 просмотров • 1 год назад

"I was all in on Miami Ohio and they earned their way in.. They're a good team and I think the committee did the right thing" ~ Seth Greenberg #PMSLive
1:53

"I was all in on Miami Ohio and they earned their way in.. They're a good team and I think the committee did the right thing" ~ Seth Greenberg #PMSLive

Pat McAfee

58,305 просмотров • 5 месяцев назад

Netanyahu on Iran: I think they are not ideological factions as much as they differ on the assessment of how tough we are. That's it. You know, those who think that Trump is very tough, they say, "Let's not confront this guy." And those who think, "No, you know, we can play America," they tend to be more demanding. Source: Fox News
0:49

Netanyahu on Iran: I think they are not ideological factions as much as they differ on the assessment of how tough we are. That's it. You know, those who think that Trump is very tough, they say, "Let's not confront this guy." And those who think, "No, you know, we can play America," they tend to be more demanding. Source: Fox News

Clash Report

37,341 просмотров • 1 месяц назад

“The Zoomers are so much better than the Millennials” Marc Andreessen 🇺🇸 on the AI-native Zoomers who learned tech from YouTube and have a burning desire to build something great: “2015 to 2024... was a very, very strange period. And a lot of just things got really weird. And the Zoomers are the generation that basically was on the receiving end of that.” “And they're not walking around feeling guilty about everything all the time. They're not feeling like they have to deny that they want to be successful.” “They've seen a thousand hours of YouTube videos from all the great people in tech talking about how to do everything. They just know so much more than previous generations of founders did.” “They're all AI native. They all basically learn AI from scratch and in college. They're coming out, and they totally understand it.” “They wear their heart on their sleeve. They're gonna build something great. And they're completely unapologetic about it.”
1:33

“The Zoomers are so much better than the Millennials” Marc Andreessen 🇺🇸 on the AI-native Zoomers who learned tech from YouTube and have a burning desire to build something great: “2015 to 2024... was a very, very strange period. And a lot of just things got really weird. And the Zoomers are the generation that basically was on the receiving end of that.” “And they're not walking around feeling guilty about everything all the time. They're not feeling like they have to deny that they want to be successful.” “They've seen a thousand hours of YouTube videos from all the great people in tech talking about how to do everything. They just know so much more than previous generations of founders did.” “They're all AI native. They all basically learn AI from scratch and in college. They're coming out, and they totally understand it.” “They wear their heart on their sleeve. They're gonna build something great. And they're completely unapologetic about it.”

a16z

132,979 просмотров • 8 месяцев назад

.President Donald J. Trump: You have sick people, and you have to mitigate the risk, but some of these sick people, they're very sick, but they're also, in some cases, very, very smart. He went to a great school. The person in Butler, he had almost 1600 on his College Boards. I think law enforcement did a great job last night.
1:21

.President Donald J. Trump: You have sick people, and you have to mitigate the risk, but some of these sick people, they're very sick, but they're also, in some cases, very, very smart. He went to a great school. The person in Butler, he had almost 1600 on his College Boards. I think law enforcement did a great job last night.

Rapid Response 47

66,010 просмотров • 4 месяцев назад

Head of Claude Code: "The model changes so often that I sometimes get stuck in this old way of thinking. I find that new people on the team do stuff in a more AGI forward way than I do. You have to transport yourself to the current moment and not get stuck back in an old model, because it's not Sonnet 3.5 anymore. The new models are just completely, completely different."
0:52

Head of Claude Code: "The model changes so often that I sometimes get stuck in this old way of thinking. I find that new people on the team do stuff in a more AGI forward way than I do. You have to transport yourself to the current moment and not get stuck back in an old model, because it's not Sonnet 3.5 anymore. The new models are just completely, completely different."

Lenny Rachitsky

71,558 просмотров • 6 месяцев назад

I did not forget about you, boys. and I know how much you all think of me. follow the command. think of me waking up tomorrow.
1:36

Sensitive content

I did not forget about you, boys. and I know how much you all think of me. follow the command. think of me waking up tomorrow.

Augustus

153,778 просмотров • 4 месяцев назад

Hassett: "People are spending more on gas, but they're also spending more on everything else -- not just groceries, but restaurants and so on. I think that's a sign you see when people are optimistic about the future."
0:52

Hassett: "People are spending more on gas, but they're also spending more on everything else -- not just groceries, but restaurants and so on. I think that's a sign you see when people are optimistic about the future."

Aaron Rupar

1,983,759 просмотров • 3 месяцев назад

ELON MUSK: Instagram makes people sad. On Instagram, people look like they have a much better life than they really do. So, by design, people are posting pictures of when they're really happy, they're modifying those pictures to be better looking, even if they're not modifying the pictures, they're at least selecting the pictures for the best lighting, the best angle, so people basically seem way better looking than they basically really are, and they're way happier seeming than they really are. So, if you look at everyone on Instagram, you might think, man, all these happy, beautiful people, and I'm not that good looking, and I am not happy, so I must suck, you know. And that's gonna feel sad. So, when in fact those people you think are super happy, actually not that happy. Some of them are really depressed, they're very sad people."
0:57

ELON MUSK: Instagram makes people sad. On Instagram, people look like they have a much better life than they really do. So, by design, people are posting pictures of when they're really happy, they're modifying those pictures to be better looking, even if they're not modifying the pictures, they're at least selecting the pictures for the best lighting, the best angle, so people basically seem way better looking than they basically really are, and they're way happier seeming than they really are. So, if you look at everyone on Instagram, you might think, man, all these happy, beautiful people, and I'm not that good looking, and I am not happy, so I must suck, you know. And that's gonna feel sad. So, when in fact those people you think are super happy, actually not that happy. Some of them are really depressed, they're very sad people."

DogeDesigner

80,922 просмотров • 4 месяцев назад

I tried Opus 4.6 Max in Cursor with a much more detailed prompt and the results are incredible Functional inventory, health, tools, recipes, and more The only downside is how expensive the model is and it also had to fix some bugs, but it's a pretty strong model overall
1:42

I tried Opus 4.6 Max in Cursor with a much more detailed prompt and the results are incredible Functional inventory, health, tools, recipes, and more The only downside is how expensive the model is and it also had to fix some bugs, but it's a pretty strong model overall

Angel 🌼

70,710 просмотров • 7 месяцев назад

So Alibaba has just released a coding plan with all the best open source models You’ve access to Qwen 3.5-Plus, Kimi K2.5, MiniMax M2.5, GLM-5, etc. And you can plug it to: - Claude Code (as I did) - OpenClaw - Codex - Cline… While being waaay cheaper than the paid plan of Codex, Claude & Cie. More below
0:36

So Alibaba has just released a coding plan with all the best open source models You’ve access to Qwen 3.5-Plus, Kimi K2.5, MiniMax M2.5, GLM-5, etc. And you can plug it to: - Claude Code (as I did) - OpenClaw - Codex - Cline… While being waaay cheaper than the paid plan of Codex, Claude & Cie. More below

Paul Couvert

88,333 просмотров • 6 месяцев назад

Cursor vs Claude Code (day 3 of 30) today I re-tested Conductor and I don't want to overhype this but... what the actual fook 😮 this thing is amazing! closest things to the "perfect workflow" I have seen in a long time, and it's something I could see myself use full-time it's so minimal and the polar opposite of Cursor but it has all the essentials → Claude Code + Codex subscriptions (= unlimited usage) → great integration with Claude Code's plan mode → multiple tabs with multiple agents at the same time → can use multiple models, not just one → great file tree and diff viewer → best git worktree support I've ever seen there's honestly so much more, like a dedicated "review" button (which you can pair to your favorite review model, e.g. gpt-5.2-extra-high), buttons to create and merge pull requests, to launch your dev server, ... this solves literally EVERY fault I can think of when using Claude Code and/or Codex, combining both into one easy UX that not only does everything the tools can do, but actually adds useful stuff on top just 6 months ago I couldn't have dreamt about any this and the wildest part is that IT IS FREE (I'd literally pay for this UX lol) first time I'm genuinely enjoying myself since starting this challenge not saying it's a full Cursor replacement yet, it obviously isn't for a lot of people (no browser, no debug mode, no code indexing, etc) ... but this is the closest thing I've seen yet 👀 follow for day 4!
5:56

Cursor vs Claude Code (day 3 of 30) today I re-tested Conductor and I don't want to overhype this but... what the actual fook 😮 this thing is amazing! closest things to the "perfect workflow" I have seen in a long time, and it's something I could see myself use full-time it's so minimal and the polar opposite of Cursor but it has all the essentials → Claude Code + Codex subscriptions (= unlimited usage) → great integration with Claude Code's plan mode → multiple tabs with multiple agents at the same time → can use multiple models, not just one → great file tree and diff viewer → best git worktree support I've ever seen there's honestly so much more, like a dedicated "review" button (which you can pair to your favorite review model, e.g. gpt-5.2-extra-high), buttons to create and merge pull requests, to launch your dev server, ... this solves literally EVERY fault I can think of when using Claude Code and/or Codex, combining both into one easy UX that not only does everything the tools can do, but actually adds useful stuff on top just 6 months ago I couldn't have dreamt about any this and the wildest part is that IT IS FREE (I'd literally pay for this UX lol) first time I'm genuinely enjoying myself since starting this challenge not saying it's a full Cursor replacement yet, it obviously isn't for a lot of people (no browser, no debug mode, no code indexing, etc) ... but this is the closest thing I've seen yet 👀 follow for day 4!

Robin Ebers

40,764 просмотров • 8 месяцев назад

made a video about how i built a website with face tracking tried to share everything i had in 3:50: how the idea came together, figma layouts, prompts, the full tech stack, and how i drew the illustrations (built it with codex + claude code in cursor, three.js mediapipe matter.js.)
3:50

made a video about how i built a website with face tracking tried to share everything i had in 3:50: how the idea came together, figma layouts, prompts, the full tech stack, and how i drew the illustrations (built it with codex + claude code in cursor, three.js mediapipe matter.js.)

Eugene Y.

10,547 просмотров • 5 месяцев назад

You probably don’t use just one AI agent anymore. Maybe Codex for coding. Claude Code for research. Cursor for quick edits. Hermes for the rest. Each one is great at something different. But every time you switch, you have to start over — re-explaining your project, preferences, and the way you like to work. Your agents know how to help you. They just don’t share a memory of you. memU just shipped an update that fixes this. One personal memory, shared across every agent and device you use. What Codex learned last night, Claude Code can remember this morning. 🧵
0:34

You probably don’t use just one AI agent anymore. Maybe Codex for coding. Claude Code for research. Cursor for quick edits. Hermes for the rest. Each one is great at something different. But every time you switch, you have to start over — re-explaining your project, preferences, and the way you like to work. Your agents know how to help you. They just don’t share a memory of you. memU just shipped an update that fixes this. One personal memory, shared across every agent and device you use. What Codex learned last night, Claude Code can remember this morning. 🧵

Hasan

22,362 просмотров • 1 месяц назад

AND THAT HE SAID. 🎙️: "antonelli said that mercedes is not the fastest car anymore and mclaren is way too fast in zandvoort. and russell said mclaren is the team to beat. is that to put pressure on you?" lando: "well, they're not going to say themselves, are they? they're not going to say that they're the team to beat, if they just got beaten today. so i don't think it's true. i think if i didn't get kimi when i overtook him, i don't think i would have won the race today. it's hard to say. but i also know how good of a job i'm doing behind the wheel, and of course i'm never one to over-talk about myself, so normally i'm always the complete opposite. but for once i will give myself a little bit of credit that i feel like i'm doing a better job than everyone, and i think that can also make a difference. we certainly have a car now capable of beating them, even like we looked at yesterday in qualifying, but we didn't win yesterday, and we didn't really change much. but i worked a lot on my driving. i want to believe more than everyone else again, and we turned things around today.."
2:05

AND THAT HE SAID. 🎙️: "antonelli said that mercedes is not the fastest car anymore and mclaren is way too fast in zandvoort. and russell said mclaren is the team to beat. is that to put pressure on you?" lando: "well, they're not going to say themselves, are they? they're not going to say that they're the team to beat, if they just got beaten today. so i don't think it's true. i think if i didn't get kimi when i overtook him, i don't think i would have won the race today. it's hard to say. but i also know how good of a job i'm doing behind the wheel, and of course i'm never one to over-talk about myself, so normally i'm always the complete opposite. but for once i will give myself a little bit of credit that i feel like i'm doing a better job than everyone, and i think that can also make a difference. we certainly have a car now capable of beating them, even like we looked at yesterday in qualifying, but we didn't win yesterday, and we didn't really change much. but i worked a lot on my driving. i want to believe more than everyone else again, and we turned things around today.."

ray

475,721 просмотров • 20 дней назад