Loading video...

Video Failed to Load

Go Home

The best way to use o1 in Cursor: Let it analyze and explain the codebase to you o1 is extremely good at this. You can jump into any new codebase and quickly get a good understanding of it

moritzkremb's profile picture

Moritz Kremb

71,612 subscribers

87,335 views • 1 year ago •via X (Twitter)

EducationScience & TechnologyNews & Politics
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

ok first impressions of claude 3.7 sonnet max on cursor VERY good at planning out your project first - seems to have way more of an understanding of the codebase i had it whip up a set of instructions to create a cursor rules tool that lets you mix/match and output in the format you want (including .cursor/rules/{rule}.mdc, .windsurfrules, .clinerules and legacy .cursorrules) still struggled with new versions of packages and i need to riff on the ui but this is impressive and i'll be using it more to plan features with!
0:17

ok first impressions of claude 3.7 sonnet max on cursor VERY good at planning out your project first - seems to have way more of an understanding of the codebase i had it whip up a set of instructions to create a cursor rules tool that lets you mix/match and output in the format you want (including .cursor/rules/{rule}.mdc, .windsurfrules, .clinerules and legacy .cursorrules) still struggled with new versions of packages and i need to riff on the ui but this is impressive and i'll be using it more to plan features with!

Ian Nuttall

37,035 views • 1 year ago

We built the best codebase search to give any agent grounded information from GitHub repos. Introducing Sandbox Search. Point it at any repo, and we’ll spin up a secure coding agent in its own sandbox to do research for you. Use inside claude code, openclaw, cursor, and more.
0:14

We built the best codebase search to give any agent grounded information from GitHub repos. Introducing Sandbox Search. Point it at any repo, and we’ll spin up a secure coding agent in its own sandbox to do research for you. Use inside claude code, openclaw, cursor, and more.

Arlan

12,412 views • 4 months ago

My project has 39,205 lines of code, and Cursor can't answer questions about it. Cursor's context seems to be capped at around 10,000 tokens. Unfortunately, this is not enough for any decent-sized project. If you have a large codebase, check out Augment Code. This thing is faaaast! I'm currently using their Visual Studio Code plugin, but you can also use them on JetBrains, Neovim, and even Vim. (I'm a Neovim fan, but Copilot's implementation for Neovim is nowhere as good as Augment Code.) Augment Code was gracious enough to sponsor this post. After you install their extension and run it for the first time, it will index your entire codebase. This is why it can answer questions as fast as it does, regardless of the size of your codebase. Augment Code supports chat and completions like every other AI coding assistant, but its killer feature is "Next Edit." When you make a change, two things happen: 1. The model analyzes the change to determine the ripple effects across your *entire* codebase. 2. The model suggests everything you need to update to ensure everything works correctly. This is pretty wild!
0:19

My project has 39,205 lines of code, and Cursor can't answer questions about it. Cursor's context seems to be capped at around 10,000 tokens. Unfortunately, this is not enough for any decent-sized project. If you have a large codebase, check out Augment Code. This thing is faaaast! I'm currently using their Visual Studio Code plugin, but you can also use them on JetBrains, Neovim, and even Vim. (I'm a Neovim fan, but Copilot's implementation for Neovim is nowhere as good as Augment Code.) Augment Code was gracious enough to sponsor this post. After you install their extension and run it for the first time, it will index your entire codebase. This is why it can answer questions as fast as it does, regardless of the size of your codebase. Augment Code supports chat and completions like every other AI coding assistant, but its killer feature is "Next Edit." When you make a change, two things happen: 1. The model analyzes the change to determine the ripple effects across your *entire* codebase. 2. The model suggests everything you need to update to ensure everything works correctly. This is pretty wild!

Santiago

247,833 views • 1 year ago

The new Cursor agent is INSANE It can run any python func in your codebase. The idea being being to check output & debug, but fuck that CRAZY SIDE EFFECT: this means you can customize the agent w/ callable tools! Like GPT Store actions or Claude MCP Cursor Agent Builder!
0:17

The new Cursor agent is INSANE It can run any python func in your codebase. The idea being being to check output & debug, but fuck that CRAZY SIDE EFFECT: this means you can customize the agent w/ callable tools! Like GPT Store actions or Claude MCP Cursor Agent Builder!

Nick Dobos

63,056 views • 1 year ago

Excited to introduce OpenAI o1—a new series of reasoning models. Developers, we’d love for you to kick the tires, but don’t just hot-swap GPT-4o with o1! Send o1-preview and o1-mini your coding tasks or hard challenges, and share your feedback and most interesting results.
0:15

Excited to introduce OpenAI o1—a new series of reasoning models. Developers, we’d love for you to kick the tires, but don’t just hot-swap GPT-4o with o1! Send o1-preview and o1-mini your coding tasks or hard challenges, and share your feedback and most interesting results.

Romain Huet

234,323 views • 2 years ago

Truth: AI coding models are good for code execution, but not good at planning. If you let AI plan next step while coding, it will mess up the codebase. You can solve this by attaching a detailed "Implementation Plan" Here's how I create my plan: ↓
0:17

Truth: AI coding models are good for code execution, but not good at planning. If you let AI plan next step while coding, it will mess up the codebase. You can solve this by attaching a detailed "Implementation Plan" Here's how I create my plan: ↓

CJ Zafir

64,900 views • 1 year ago

Introducing o1 web crawler 🕸️ It crawls entire websites with OpenAI’s new o1 reasoning model and . Just state an objective and it will navigate + return the requested data in a JSON schema. Check it out:
0:17

Introducing o1 web crawler 🕸️ It crawls entire websites with OpenAI’s new o1 reasoning model and . Just state an objective and it will navigate + return the requested data in a JSON schema. Check it out:

Eric Ciarla (hiring)

397,759 views • 1 year ago

This was us haha. Sreejith PP Arpit Saxena and I built Andrej Karpathy-fy! It takes a paperswithcode link, your current proficiency and gives you a tailored 5 lesson plan to go from where you are to the meaty parts of the paper implementation - like the karpathy video series / labml style. This is a task none of the previous models could do, and O1 was really good at. The best part? The output is an executable ipynb notebook (which you can use minusxai to work through :) ) The below video has apple's recent monocular depth paper. I could actually go through and understand it, with loss functions from the paper and everything!
0:14

This was us haha. Sreejith PP Arpit Saxena and I built Andrej Karpathy-fy! It takes a paperswithcode link, your current proficiency and gives you a tailored 5 lesson plan to go from where you are to the meaty parts of the paper implementation - like the karpathy video series / labml style. This is a task none of the previous models could do, and O1 was really good at. The best part? The output is an executable ipynb notebook (which you can use minusxai to work through :) ) The below video has apple's recent monocular depth paper. I could actually go through and understand it, with loss functions from the paper and everything!

Vivek Aithal

200,848 views • 1 year ago

im not as good as it as i used to but the gist is: jump and hold forward, when you land you have to let go of forward and flick your mouse to the side and then jump again and then press forward again. it's really fun when you get the hang of it. i dont have revolvers on dis sav
0:10

im not as good as it as i used to but the gist is: jump and hold forward, when you land you have to let go of forward and flick your mouse to the side and then jump again and then press forward again. it's really fun when you get the hang of it. i dont have revolvers on dis sav

Paige

557,833 views • 1 year ago

Wow.. you can now instantly turn any GitHub repo into AI-generated documentation, just by changing the URL. Replace “github” with “deepwiki” in any GitHub URL and you’ll see: → Instant docs for any codebase → Chat with it like a conversation
0:11

Wow.. you can now instantly turn any GitHub repo into AI-generated documentation, just by changing the URL. Replace “github” with “deepwiki” in any GitHub URL and you’ll see: → Instant docs for any codebase → Chat with it like a conversation

Oliver Prompts

122,082 views • 6 months ago

you don't need to re-explain your codebase's architecture to your agent every session. most tools stop at telling you what broke. sentrux is a real-time architectural sensor, it watches your codebase as a live treemap and turns file structure and dependencies into one continuous quality score. the loop is simple: codebase > agent scans structure and dependencies > sentrux scores 5 root cause metrics into one signal > agent sees exactly where risk concentrates > next session starts from a live map instead of a blind grep the binary carries zero built-in language knowledge, all 52 languages live in plugin.toml and tags.scm query files, so a new language needs zero rust code. small catch: it only scores the structure, it won't tell you why the cycle happened, that part's still on you. built pure Rust with no runtime dependencies, specifically so it could sit as one binary between an agent and a codebase without adding friction.
0:10

you don't need to re-explain your codebase's architecture to your agent every session. most tools stop at telling you what broke. sentrux is a real-time architectural sensor, it watches your codebase as a live treemap and turns file structure and dependencies into one continuous quality score. the loop is simple: codebase > agent scans structure and dependencies > sentrux scores 5 root cause metrics into one signal > agent sees exactly where risk concentrates > next session starts from a live map instead of a blind grep the binary carries zero built-in language knowledge, all 52 languages live in plugin.toml and tags.scm query files, so a new language needs zero rust code. small catch: it only scores the structure, it won't tell you why the cycle happened, that part's still on you. built pure Rust with no runtime dependencies, specifically so it could sit as one binary between an agent and a codebase without adding friction.

Simplifying AI

18,308 views • 24 days ago

The then and now of this Country! Everyone can literally look this up to fact check it too! Just to let some of you know the Blue is good and the red is bad!
0:18

The then and now of this Country! Everyone can literally look this up to fact check it too! Just to let some of you know the Blue is good and the red is bad!

Suzie rizzio

871,342 views • 8 months ago

The way you track token unlocks is about to change. Our new Token Unlocks Dashboard gives you a market-wide view of upcoming unlocks. This way you catch and analyze crucial events before they impact prices: 🔗 Here’s how to use it to stay ahead 🧵
0:16

The way you track token unlocks is about to change. Our new Token Unlocks Dashboard gives you a market-wide view of upcoming unlocks. This way you catch and analyze crucial events before they impact prices: 🔗 Here’s how to use it to stay ahead 🧵

CryptoRank.io

84,567 views • 1 year ago

short thread to recap this new workflow on Kling O1 1. choose an image or create it 2. create more cinematic angles in a grid (Higgsfield cinema studio or directly in NanoBanana) 3. add the grid into Kling O1 (add more references if needed)
0:10

short thread to recap this new workflow on Kling O1 1. choose an image or create it 2. create more cinematic angles in a grid (Higgsfield cinema studio or directly in NanoBanana) 3. add the grid into Kling O1 (add more references if needed)

INK

47,402 views • 8 months ago

setting. cadence. influencer realism. story. product. audience. that's what actually makes AI UGC work seedance 2.0 is the best at all of those things good start frame + my V2 prompting system and it handles b-roll, cuts, voiceover, everything you don't need better tools. we're already at the best it can get you just need to know how to use it properly...
0:15

setting. cadence. influencer realism. story. product. audience. that's what actually makes AI UGC work seedance 2.0 is the best at all of those things good start frame + my V2 prompting system and it handles b-roll, cuts, voiceover, everything you don't need better tools. we're already at the best it can get you just need to know how to use it properly...

Miko

16,697 views • 6 months ago

Before you really can be good at the game, you gotta love the game. Just let them get out there and enjoy the game because once they develop that love, then they want to learn and listen to the people that want to teach them. You gotta have a passion for something to be good at it.
0:17

Before you really can be good at the game, you gotta love the game. Just let them get out there and enjoy the game because once they develop that love, then they want to learn and listen to the people that want to teach them. You gotta have a passion for something to be good at it.

The Winning Difference

18,261 views • 1 year ago

Code reviews Codex goes beyond static analysis—it checks a PR against its intent, reasons across the codebase and dependencies, and can run code to validate the behavior of changes. Set it up to auto-review new PRs in your repo, or tag @ codex.
0:13

Code reviews Codex goes beyond static analysis—it checks a PR against its intent, reasons across the codebase and dependencies, and can run code to validate the behavior of changes. Set it up to auto-review new PRs in your repo, or tag @ codex.

OpenAI Developers

60,331 views • 1 year ago

This Wyatt Langford catch from yesterday is a great example of why catch probability is good to know. Just a 45% catch probability here. Why? Any MLB outfielder catches this ball if they get there. Most can't get there. Langford's jump is elite, +8.7 feet above the average outfielder. The jump is so good he doesn't even have to get up to top speed. This is just a routine double into the gap much of the time, and the TV viewer thinks nothing of it:
0:11

This Wyatt Langford catch from yesterday is a great example of why catch probability is good to know. Just a 45% catch probability here. Why? Any MLB outfielder catches this ball if they get there. Most can't get there. Langford's jump is elite, +8.7 feet above the average outfielder. The jump is so good he doesn't even have to get up to top speed. This is just a routine double into the gap much of the time, and the TV viewer thinks nothing of it:

The WARmonger

324,332 views • 1 year ago