Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Never bet against Cursor. Subagents solve so many issues between different models it's kind of insane, especially with Composer 1. Composer 1 can quickly gather context for a model like GPT-5.2 Codex, which otherwise could take on the order of 10 mins just to search files. Definitely one of... show more

ostyn

1,690 subscribers

19,631 views • 5 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🚨You can now use the new upcoming OpenAI model GPT 5.2 inside Cursor. Here is the full walkthrough. - Open the editor, go to settings and then the model tab. Add a custom model and enter the text "gpt-5.2-high" and "gpt-5.2". - After that you can select the model and ask questions. To verify, I started my test on the usage page which had zero gpt-5.2-high requests and consumption. After the test I could see the details in usage and the cost incurred while using it. Enjoy

🚨You can now use the new upcoming OpenAI model GPT 5.2 inside Cursor. Here is the full walkthrough. - Open the editor, go to settings and then the model tab. Add a custom model and enter the text "gpt-5.2-high" and "gpt-5.2". - After that you can select the model and ask questions. To verify, I started my test on the usage page which had zero gpt-5.2-high requests and consumption. After the test I could see the details in usage and the cost incurred while using it. Enjoy

AshutoshShrivastava

424,035 views • 7 months ago

Warp now supports GPT 5.2 Codex 🙌 We worked closely with the OpenAI team to tune our harness for the Codex series. GPT 5.2 Codex builds upon the strengths of GPT 5.2, excelling at long-horizon tasks (think 15 min+) Try GPT 5.2 codex and tell us what you think

Warp now supports GPT 5.2 Codex 🙌 We worked closely with the OpenAI team to tune our harness for the Codex series. GPT 5.2 Codex builds upon the strengths of GPT 5.2, excelling at long-horizon tasks (think 15 min+) Try GPT 5.2 codex and tell us what you think

Warp

32,708 views • 5 months ago

Sam Altman says the perfect AI is “a very tiny model with superhuman reasoning, 1 trillion tokens of context, and access to every tool you can imagine.” It doesn't need to contain the knowledge - just the ability to think, search, simulate, and solve anything.

Sam Altman says the perfect AI is “a very tiny model with superhuman reasoning, 1 trillion tokens of context, and access to every tool you can imagine.” It doesn't need to contain the knowledge - just the ability to think, search, simulate, and solve anything.

vitrupo

775,766 views • 1 year ago

In this episode, Beyang and Thorsten discuss strategies for effective agentic coding, including the 101 of how it's different from coding with chat LLMs, the key constraint of the context window, how and where subagents can help, and the new oracle subagent which combines multiple LLMs. 00:38 Intros 03:20 How coding with agents is very different from coding with prior AI tools 10:31 Example: fix a simple issue 14:13 Example: debugging an issue with an MCP server 21:50 Example: unifying two build scripts 25:09 How the context window is a key constraint 31:01 Why it's best to focus on one thing at a time 33:09 Subagents and context windows 33:49 The codebase search subagent 38:33 General-purpose subagents 44:05 When to use subagents 46:44 The oracle subagent and o3 51:32 Multi-model agents

In this episode, Beyang and Thorsten discuss strategies for effective agentic coding, including the 101 of how it's different from coding with chat LLMs, the key constraint of the context window, how and where subagents can help, and the new oracle subagent which combines multiple LLMs. 00:38 Intros 03:20 How coding with agents is very different from coding with prior AI tools 10:31 Example: fix a simple issue 14:13 Example: debugging an issue with an MCP server 21:50 Example: unifying two build scripts 25:09 How the context window is a key constraint 31:01 Why it's best to focus on one thing at a time 33:09 Subagents and context windows 33:49 The codebase search subagent 38:33 General-purpose subagents 44:05 When to use subagents 46:44 The oracle subagent and o3 51:32 Multi-model agents

Amp — Research Preview

24,534 views • 11 months ago

I've made a ton of money helping companies implement LLM-as-a-judge evaluations. LLM Judges provide a ton of value. But the hard part is choosing the model to implement the judge. • The family of GPT-5 models is very good, but slow and expensive. • Models like Gemma and Phi are fast and cheap, but not that good. Most of the time, you can only run a percentage of your traffic through the model (otherwise it would be too expensive and slow). But now, there's a better strategy.

I've made a ton of money helping companies implement LLM-as-a-judge evaluations. LLM Judges provide a ton of value. But the hard part is choosing the model to implement the judge. • The family of GPT-5 models is very good, but slow and expensive. • Models like Gemma and Phi are fast and cheap, but not that good. Most of the time, you can only run a percentage of your traffic through the model (otherwise it would be too expensive and slow). But now, there's a better strategy.

Santiago

29,916 views • 2 months ago

The Copilot CLI now supports builtin subagents for parallelizing search and coding tasks within separate context windows. Uniquely, the outer agent can invoke different models. Ask Opus, Codex, Gemini and a dozen other models for answers in parallel.

The Copilot CLI now supports builtin subagents for parallelizing search and coding tasks within separate context windows. Uniquely, the outer agent can invoke different models. Ask Opus, Codex, Gemini and a dozen other models for answers in parallel.

Evan Boyle

10,602 views • 6 months ago

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

Santiago

384,495 views • 3 years ago

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 views • 2 years ago

One of Blender's powerful capabilities is how quickly you can create models and concepts of just about anything. Here you can see how I create a simple model of motor rotor with electromagnets, you can use geometry nodes to speed up your modelling workflow even more and also make them procedural with animations, and it's a lot of fun too! #b3d #blender3d #electronics #hardware #science #engineering #technology #3dart #3DModel #motors

One of Blender's powerful capabilities is how quickly you can create models and concepts of just about anything. Here you can see how I create a simple model of motor rotor with electromagnets, you can use geometry nodes to speed up your modelling workflow even more and also make them procedural with animations, and it's a lot of fun too! #b3d #blender3d #electronics #hardware #science #engineering #technology #3dart #3DModel #motors

Sam M

18,239 views • 1 year ago

The new SpaceX-Cursor model is going to be insane. It is being trained from scratch, unlike previous Composer models, which were built off Kimi. This new model is Elon’s attempt to get back in the AI race, and he might rejoin as the frontrunner. Composer 2.5 is already a world-class model, only losing to models like GPT-5.5, Opus 4.8, and Fable 5. Grok Composer 3, with SpaceX’s massive compute and xAI’s team, could become the best AI model on the planet. Elon is back.

The new SpaceX-Cursor model is going to be insane. It is being trained from scratch, unlike previous Composer models, which were built off Kimi. This new model is Elon’s attempt to get back in the AI race, and he might rejoin as the frontrunner. Composer 2.5 is already a world-class model, only losing to models like GPT-5.5, Opus 4.8, and Fable 5. Grok Composer 3, with SpaceX’s massive compute and xAI’s team, could become the best AI model on the planet. Elon is back.

Ali Romman

119,837 views • 22 days ago

Robert Benzie: "What Danielle Smith has done is open a can of worms to solve a problem within the United Conservative Party just as David Cameron opened a can of worms to solve a problem in the UK Conservative Party ... why would you ask a question at the risk of finding an answer that you don't want. I think it's just insane on many levels."

Robert Benzie: "What Danielle Smith has done is open a can of worms to solve a problem within the United Conservative Party just as David Cameron opened a can of worms to solve a problem in the UK Conservative Party ... why would you ask a question at the risk of finding an answer that you don't want. I think it's just insane on many levels."

Scott Robertson

40,503 views • 2 months ago

Very impressed with Composer 2.5 after about a day of usage. I've almost moved over to it exclusively from GPT 5.5, even using it for planning now. It's like Opus 4.7 on steroids, crazy fast. Fast models really get me into the flow of building, which is exhilarating. Also, a sneak peek of a weekend mini-project I'm building: a racing game where you race your mouse cursor.

Very impressed with Composer 2.5 after about a day of usage. I've almost moved over to it exclusively from GPT 5.5, even using it for planning now. It's like Opus 4.7 on steroids, crazy fast. Fast models really get me into the flow of building, which is exhilarating. Also, a sneak peek of a weekend mini-project I'm building: a racing game where you race your mouse cursor.

Danny Limanseta

299,034 views • 1 month ago

Reflections after a day on Sora 2: It's a huge step up over the first model from a quality perspective. I'm not sure it's SOTA - but I don't think that matters. This isn't competing with other video models, it's much more of a social app. Beyond Cameos, I think the strongest feature is remixing. You can take a clip that someone else generated and prompt changes, which feels like riffing with friends. And you eliminate most of the work around prompting, which is kind of genius. Many people don't use video models today because they don't know what to create. Here, you can scroll until you get inspired. The best videos often have dozens of remixes, like this example ⬇️

Reflections after a day on Sora 2: It's a huge step up over the first model from a quality perspective. I'm not sure it's SOTA - but I don't think that matters. This isn't competing with other video models, it's much more of a social app. Beyond Cameos, I think the strongest feature is remixing. You can take a clip that someone else generated and prompt changes, which feels like riffing with friends. And you eliminate most of the work around prompting, which is kind of genius. Many people don't use video models today because they don't know what to create. Here, you can scroll until you get inspired. The best videos often have dozens of remixes, like this example ⬇️

Justine Moore

61,291 views • 9 months ago

Generalist CEO Pete Florence says robotics models are in a transition period similar to the step change between GPT-2 and GPT-3. They're "starting to cross over into levels of performance where these things are commercially viable for a number of different applications." "We think this is a crossover point where we have a general model starting to be able to hit levels of reliability, speed, and improvisational intelligence where we can start to get these things out there." "Very much like — you take a GPT-2-level model, you scale it to a GPT-3-level model, and certain types of commercial applications start to become viable."

Generalist CEO Pete Florence says robotics models are in a transition period similar to the step change between GPT-2 and GPT-3. They're "starting to cross over into levels of performance where these things are commercially viable for a number of different applications." "We think this is a crossover point where we have a general model starting to be able to hit levels of reliability, speed, and improvisational intelligence where we can start to get these things out there." "Very much like — you take a GPT-2-level model, you scale it to a GPT-3-level model, and certain types of commercial applications start to become viable."

TBPN

22,980 views • 1 month ago

After a couple more days with Composer 2.5, I've got a pretty good sense of what it can do for game dev, specifically this mouse cursor racing game I'm building. It nailed ~80% of the features I threw at it, from planning to execution. Pretty amazing. I did have to switch to Opus 4.7 MAX a few times for features that need stronger visual understanding, like adding a 360 loop to the track or nailing a specific visual effect I had in mind. But man, Opus 4.7 MAX is expensive. Composer 2.5's visual understanding is weaker than Opus 4.7, but for most other things it's pretty damn close, and 10x cheaper. So it's now my default. The beauty of Cursor is I can switch models whenever I want, so I'm never stuck on one. Really excited for the larger incoming model. I have a feeling it's going to shine at planning. Can't wait!

After a couple more days with Composer 2.5, I've got a pretty good sense of what it can do for game dev, specifically this mouse cursor racing game I'm building. It nailed ~80% of the features I threw at it, from planning to execution. Pretty amazing. I did have to switch to Opus 4.7 MAX a few times for features that need stronger visual understanding, like adding a 360 loop to the track or nailing a specific visual effect I had in mind. But man, Opus 4.7 MAX is expensive. Composer 2.5's visual understanding is weaker than Opus 4.7, but for most other things it's pretty damn close, and 10x cheaper. So it's now my default. The beauty of Cursor is I can switch models whenever I want, so I'm never stuck on one. Really excited for the larger incoming model. I have a feeling it's going to shine at planning. Can't wait!

Danny Limanseta

171,643 views • 1 month ago

I JUST DROPPED A NEW SONG! It's a remix for an upcoming video, but you can listen to the full song RIGHT NOW STREAM "Tears of the Kitchen"

I JUST DROPPED A NEW SONG! It's a remix for an upcoming video, but you can listen to the full song RIGHT NOW STREAM "Tears of the Kitchen"

JayMoji 🪐

30,889 views • 1 year ago

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.

OpenAI

3,635,813 views • 2 months ago

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:

Santiago

324,586 views • 2 years ago