Stop Wasting Money on the Wrong AI

Coinbase, Cursor, Lindy, lots of Coinbase, Cursor, Lindy, lots of companies are switching to open source companies are switching to open source companies are switching to open source models. This video's not about them. models. This video's not about them. models. This video's not about them. This video's for you. This video helps This video's for you. This video helps This video's for you. This video helps you sort through the noise and pick a you sort through the noise and pick a you sort through the noise and pick a model in a world that has exploded with model in a world that has exploded with model in a world that has exploded with model choice just in the last couple of model choice just in the last couple of model choice just in the last couple of weeks. Because since Fable was banned, weeks. Because since Fable was banned, weeks. Because since Fable was banned, so on Wednesday, July 1st, Fable 5 came so on Wednesday, July 1st, Fable 5 came so on Wednesday, July 1st, Fable 5 came back online. Yay, but here's what isn't back online. Yay, but here's what isn't back online. Yay, but here's what isn't coming back. The month where everyone coming back. The month where everyone coming back. The month where everyone assumed the model you build on will assumed the model you build on will assumed the model you build on will still be there tomorrow. Because for 18 still be there tomorrow. Because for 18 still be there tomorrow. Because for 18 days, a lot of companies found out it days, a lot of companies found out it days, a lot of companies found out it might not be. And the ones who could might not be. And the ones who could might not be. And the ones who could shrug it off were the ones who never shrug it off were the ones who never shrug it off were the ones who never tied their work to a single model in the tied their work to a single model in the tied their work to a single model in the first place because they own the first place because they own the first place because they own the harness. They routed somewhere else and harness. They routed somewhere else and harness. They routed somewhere else and they kept moving. And that's what a lot they kept moving. And that's what a lot they kept moving. And that's what a lot of companies did. This video isn't about of companies did. This video isn't about of companies did. This video isn't about whether Fable's back, right? It's about whether Fable's back, right? It's about whether Fable's back, right? It's about making sure it never matters that it was making sure it never matters that it was making sure it never matters that it was gone at all. And I am seeing a trap that a lot of And I am seeing a trap that a lot of people are falling into where they people are falling into where they people are falling into where they confuse the act of picking a model with confuse the act of picking a model with confuse the act of picking a model with getting real work done. So in this getting real work done. So in this getting real work done. So in this video, I'm going to walk you through how video, I'm going to walk you through how video, I'm going to walk you through how I think about picking a model. I'm going I think about picking a model. I'm going I think about picking a model. I'm going to walk you through why. I'm going to to walk you through why. I'm going to to walk you through why. I'm going to walk you through the pieces you need to walk you through the pieces you need to walk you through the pieces you need to think about along the way and I'm going think about along the way and I'm going think about along the way and I'm going to give you specific tips for specific to give you specific tips for specific to give you specific tips for specific models. Yes, Jill M 5.2. Yes, Qwen. Yes, models. Yes, Jill M 5.2. Yes, Qwen. Yes, models. Yes, Jill M 5.2. Yes, Qwen. Yes, Kimmy. Yes, ChatGPT. Yes, Claude. And Kimmy. Yes, ChatGPT. Yes, Claude. And Kimmy. Yes, ChatGPT. Yes, Claude. And how I think about putting them together.

how I think about putting them together. how I think about putting them together. And I'm going to give you And I'm going to give you And I'm going to give you recommendations to simplify. Like what recommendations to simplify. Like what recommendations to simplify. Like what it looks like to actually simplify in it looks like to actually simplify in it looks like to actually simplify in different roles. Whether you're a team different roles. Whether you're a team different roles. Whether you're a team lead, whether you're an individual lead, whether you're an individual lead, whether you're an individual inside a company, whether you're your inside a company, whether you're your inside a company, whether you're your own business driver and owner, whether own business driver and owner, whether own business driver and owner, whether you're a developer, whatever that role you're a developer, whatever that role you're a developer, whatever that role may be for you. How you start to think may be for you. How you start to think may be for you. How you start to think about picking models in an age when open about picking models in an age when open about picking models in an age when open source models are becoming more source models are becoming more source models are becoming more significant and how to do that in a way significant and how to do that in a way significant and how to do that in a way that actually gets you focused on the that actually gets you focused on the that actually gets you focused on the work and not distracted. All right, work and not distracted. All right, work and not distracted. All right, let's jump into it. Given where we are let's jump into it. Given where we are let's jump into it. Given where we are in the model landscape today, how do you in the model landscape today, how do you in the model landscape today, how do you make sure that picking a model is not make sure that picking a model is not make sure that picking a model is not your second job and instead you're your second job and instead you're your second job and instead you're focused on the work? focused on the work? focused on the work? Here's the frame I want you to use. A Here's the frame I want you to use. A Here's the frame I want you to use. A daily driver needs to be good across a daily driver needs to be good across a daily driver needs to be good across a wide range of use cases because it is wide range of use cases because it is wide range of use cases because it is the model you reach for before the task the model you reach for before the task the model you reach for before the task is clean. A cheap workhorse earns its is clean. A cheap workhorse earns its is clean. A cheap workhorse earns its place when the job is familiar and place when the job is familiar and place when the job is familiar and repeatable and easy to understand. And repeatable and easy to understand. And repeatable and easy to understand. And so, I would suggest that the useful so, I would suggest that the useful so, I would suggest that the useful answer begins with the work in front of answer begins with the work in front of answer begins with the work in front of you. Before you pick the model, think you. Before you pick the model, think you. Before you pick the model, think about what you want the model to do. about what you want the model to do. about what you want the model to do. Those questions matter more than the Those questions matter more than the Those questions matter more than the name on the model card, right? Ask name on the model card, right? Ask name on the model card, right? Ask whether you need it to act as a coding whether you need it to act as a coding whether you need it to act as a coding agent, ask whether you need it to make agent, ask whether you need it to make agent, ask whether you need it to make PowerPoints or spreadsheets, whatever it PowerPoints or spreadsheets, whatever it PowerPoints or spreadsheets, whatever it is, and then get to the model. And this is, and then get to the model. And this is, and then get to the model. And this is where GLM 5.2 is interesting because is where GLM 5.2 is interesting because is where GLM 5.2 is interesting because GLM 5.2 is good in a lot of center of GLM 5.2 is good in a lot of center of GLM 5.2 is good in a lot of center of distribution work. So, stuff that I distribution work. So, stuff that I distribution work. So, stuff that I think of as normal and not too heavy. A think of as normal and not too heavy. A think of as normal and not too heavy. A normal PowerPoint, a landing page draft, normal PowerPoint, a landing page draft, normal PowerPoint, a landing page draft, a meeting summary, a lot of code work a meeting summary, a lot of code work a meeting summary, a lot of code work that has familiar shapes to it where you that has familiar shapes to it where you that has familiar shapes to it where you can say, "Here's the file, just work on can say, "Here's the file, just work on can say, "Here's the file, just work on it." That's actually a massive category

it." That's actually a massive category it." That's actually a massive category of work. Most people spend most of their of work. Most people spend most of their of work. Most people spend most of their work day producing familiar artifacts work day producing familiar artifacts work day producing familiar artifacts under time pressure. And so, having the under time pressure. And so, having the under time pressure. And so, having the ability to make a table or note or a ability to make a table or note or a ability to make a table or note or a support reply or whatever very quickly support reply or whatever very quickly support reply or whatever very quickly with a cheap strong model is great. And with a cheap strong model is great. And with a cheap strong model is great. And I do want to be clear about the I do want to be clear about the I do want to be clear about the non-coding part. A lot of the current non-coding part. A lot of the current non-coding part. A lot of the current GLM conversation is coding heavy because GLM conversation is coding heavy because GLM conversation is coding heavy because coding is easy to benchmark, the savings coding is easy to benchmark, the savings coding is easy to benchmark, the savings are visible, etc. But, center of are visible, etc. But, center of are visible, etc. But, center of distribution work includes web pages and distribution work includes web pages and distribution work includes web pages and PowerPoints and memos and CRM cleanups PowerPoints and memos and CRM cleanups PowerPoints and memos and CRM cleanups and routine synthesis and all the normal and routine synthesis and all the normal and routine synthesis and all the normal business artifacts people make every business artifacts people make every business artifacts people make every day. If the shape is familiar and day. If the shape is familiar and day. If the shape is familiar and reviewing it is easy, GLM belongs in the reviewing it is easy, GLM belongs in the reviewing it is easy, GLM belongs in the conversation. Frontier models need to conversation. Frontier models need to conversation. Frontier models need to earn their keep elsewhere. I still want earn their keep elsewhere. I still want earn their keep elsewhere. I still want Claude and ChatGPT's newest models when Claude and ChatGPT's newest models when Claude and ChatGPT's newest models when the shape of work is not obvious yet. If the shape of work is not obvious yet. If the shape of work is not obvious yet. If I'm trying to find the angle in a messy I'm trying to find the angle in a messy I'm trying to find the angle in a messy sort of bundle of sources, if I'm trying sort of bundle of sources, if I'm trying sort of bundle of sources, if I'm trying to like figure out where my taste and to like figure out where my taste and to like figure out where my taste and judgment matter on a tough problem, if I judgment matter on a tough problem, if I judgment matter on a tough problem, if I have to decide where to push the model have to decide where to push the model have to decide where to push the model into a new piece of work I've not done into a new piece of work I've not done into a new piece of work I've not done before, I don't want to optimize for before, I don't want to optimize for before, I don't want to optimize for cost, I want to get it right. So, if cost, I want to get it right. So, if cost, I want to get it right. So, if you're just trying to choose a daily you're just trying to choose a daily you're just trying to choose a daily driver, that's the conversation I would driver, that's the conversation I would driver, that's the conversation I would have. Your daily driver should be the have. Your daily driver should be the have. Your daily driver should be the model you trust for messy next human model you trust for messy next human model you trust for messy next human work. Now, in my previous video, I work. Now, in my previous video, I work. Now, in my previous video, I shared I'm still using Codex for that shared I'm still using Codex for that shared I'm still using Codex for that because I find the harness is so easy to because I find the harness is so easy to because I find the harness is so easy to use that the intelligence inside it is use that the intelligence inside it is use that the intelligence inside it is not the most significant piece. But, not the most significant piece. But, not the most significant piece. But, there are a lot of other harnesses out there are a lot of other harnesses out there are a lot of other harnesses out there and that's not the only one that's there and that's not the only one that's there and that's not the only one that's effective, and you should be looking at

effective, and you should be looking at effective, and you should be looking at other harnesses that work for you, other harnesses that work for you, other harnesses that work for you, whether they're open-source harnesses, whether they're open-source harnesses, whether they're open-source harnesses, whether they are closed-source harnesses whether they are closed-source harnesses whether they are closed-source harnesses like Claude or Claude Code. Whatever like Claude or Claude Code. Whatever like Claude or Claude Code. Whatever harness you choose, make sure that you harness you choose, make sure that you harness you choose, make sure that you are deliberately picking something that are deliberately picking something that are deliberately picking something that feels like it helps you do the work and feels like it helps you do the work and feels like it helps you do the work and doesn't distract you. If costs are a doesn't distract you. If costs are a doesn't distract you. If costs are a distraction, distraction, distraction, think about a harness for GLM 5.2 that think about a harness for GLM 5.2 that think about a harness for GLM 5.2 that works for you. And yes, works for you. And yes, works for you. And yes, they released one called Z.AI, that they released one called Z.AI, that they released one called Z.AI, that should be very helpful. This is the should be very helpful. This is the should be very helpful. This is the difference between GLM style work and difference between GLM style work and difference between GLM style work and what I'm calling a fable-style problem. what I'm calling a fable-style problem. what I'm calling a fable-style problem. In a fable-type ask, the hard part is In a fable-type ask, the hard part is In a fable-type ask, the hard part is not just producing a familiar artifact not just producing a familiar artifact not just producing a familiar artifact cheaply. The hard part is understanding cheaply. The hard part is understanding cheaply. The hard part is understanding what a new capability means across what a new capability means across what a new capability means across video, across physics, across character video, across physics, across character video, across physics, across character intent, legal exposure, business intent, legal exposure, business intent, legal exposure, business strategy. You're asking the model to strategy. You're asking the model to strategy. You're asking the model to help you discover the shape of a new help you discover the shape of a new help you discover the shape of a new type of problem. And this is where I type of problem. And this is where I type of problem. And this is where I want the broadest, strongest, weirdest want the broadest, strongest, weirdest want the broadest, strongest, weirdest generalization I can get, plus a harness generalization I can get, plus a harness generalization I can get, plus a harness that can keep that context together. So, that can keep that context together. So, that can keep that context together. So, if you're just trying to choose a daily if you're just trying to choose a daily if you're just trying to choose a daily driver as an individual person, that's driver as an individual person, that's driver as an individual person, that's the that's the background matrix I would the that's the background matrix I would the that's the background matrix I would have. That's the way I would think about have. That's the way I would think about have. That's the way I would think about it. Look at where you need to do messy, it. Look at where you need to do messy, it. Look at where you need to do messy, complex work and then trust that to a complex work and then trust that to a complex work and then trust that to a frontier model maker. And look at where frontier model maker. And look at where frontier model maker. And look at where you need to do familiar work and you need to do familiar work and you need to do familiar work and consider whether something like GLM 5.2 consider whether something like GLM 5.2 consider whether something like GLM 5.2 is going to save you money at that is going to save you money at that is going to save you money at that point. Because it might Once you have a point. Because it might Once you have a point. Because it might Once you have a daily driver, take it for a drive. Test daily driver, take it for a drive. Test daily driver, take it for a drive. Test it. Put the inputs in that you care it. Put the inputs in that you care it. Put the inputs in that you care about. Maybe it's spreadsheets, maybe about. Maybe it's spreadsheets, maybe about. Maybe it's spreadsheets, maybe it's PowerPoint stuff, maybe it's docs, it's PowerPoint stuff, maybe it's docs, it's PowerPoint stuff, maybe it's docs, maybe it's PDFs, maybe it's code.

maybe it's PDFs, maybe it's code. maybe it's PDFs, maybe it's code. Whatever it is, make sure that you don't Whatever it is, make sure that you don't Whatever it is, make sure that you don't validate it as your daily driver till validate it as your daily driver till validate it as your daily driver till you actually run it across the tasks you actually run it across the tasks you actually run it across the tasks that you care about. And that's where that you care about. And that's where that you care about. And that's where you're going to find out just how you're going to find out just how you're going to find out just how complex your asks actually are. I think complex your asks actually are. I think complex your asks actually are. I think we humans are sometimes better at we humans are sometimes better at we humans are sometimes better at estimating complexity once we do the estimating complexity once we do the estimating complexity once we do the task than we are in advance. So, make task than we are in advance. So, make task than we are in advance. So, make sure you test it. Now, if you're at sure you test it. Now, if you're at sure you test it. Now, if you're at work, you may not have the freedom to work, you may not have the freedom to work, you may not have the freedom to choose a model. If you're using AI choose a model. If you're using AI choose a model. If you're using AI inside a company, the first filter's inside a company, the first filter's inside a company, the first filter's going to be permission. If you have a going to be permission. If you have a going to be permission. If you have a choice of more than one model inside a choice of more than one model inside a choice of more than one model inside a company, you should be using the same company, you should be using the same company, you should be using the same thinking process here to pick what you thinking process here to pick what you thinking process here to pick what you would use, whether that's with Microsoft would use, whether that's with Microsoft would use, whether that's with Microsoft Copilot or Claude Teams or Gemini or Copilot or Claude Teams or Gemini or Copilot or Claude Teams or Gemini or ChatGPT Enterprise. Regardless, you want ChatGPT Enterprise. Regardless, you want ChatGPT Enterprise. Regardless, you want to be taking your actual work, reliably to be taking your actual work, reliably to be taking your actual work, reliably testing it across these different testing it across these different testing it across these different models, and then picking a daily driver models, and then picking a daily driver models, and then picking a daily driver as you find actual utility matches your as you find actual utility matches your as you find actual utility matches your ask. And where it doesn't, if you're ask. And where it doesn't, if you're ask. And where it doesn't, if you're inside a company, that should be your inside a company, that should be your inside a company, that should be your cue to say, "Hey, I need a more powerful cue to say, "Hey, I need a more powerful cue to say, "Hey, I need a more powerful model. I need to work with the IT model. I need to work with the IT model. I need to work with the IT department to level up the models department to level up the models department to level up the models because look at the result that I'm because look at the result that I'm because look at the result that I'm getting here. This is not my prompting getting here. This is not my prompting getting here. This is not my prompting issue. Uh this is actually the model issue. Uh this is actually the model issue. Uh this is actually the model unable to get the work done." Now, if unable to get the work done." Now, if unable to get the work done." Now, if you run a small business or you have a you run a small business or you have a you run a small business or you have a small team, you're going to have a small team, you're going to have a small team, you're going to have a little bit more flexibility, and you little bit more flexibility, and you little bit more flexibility, and you should be thinking a ton about the level should be thinking a ton about the level should be thinking a ton about the level of energy you put into work in order to of energy you put into work in order to of energy you put into work in order to get to outputs that are really, really get to outputs that are really, really get to outputs that are really, really high quality for your customers. Because high quality for your customers. Because high quality for your customers. Because really, your ability to meet customer really, your ability to meet customer really, your ability to meet customer needs and scale is a function of your needs and scale is a function of your needs and scale is a function of your team's ability to work with models team's ability to work with models team's ability to work with models efficiently. So, ask yourself, do you

efficiently. So, ask yourself, do you efficiently. So, ask yourself, do you want a 20 model routing system, or do want a 20 model routing system, or do want a 20 model routing system, or do you want to pick the five recurring you want to pick the five recurring you want to pick the five recurring artifacts that are most critical to artifacts that are most critical to artifacts that are most critical to customers and figure out how to draw a customers and figure out how to draw a customers and figure out how to draw a straight line to value from that into straight line to value from that into straight line to value from that into the process your team uses to make sure the process your team uses to make sure the process your team uses to make sure it's as clean and simple as possible to it's as clean and simple as possible to it's as clean and simple as possible to get that artifact generated with AI. get that artifact generated with AI. get that artifact generated with AI. That's how I think about it, right? You That's how I think about it, right? You That's how I think about it, right? You think about what is the simplest way to think about what is the simplest way to think about what is the simplest way to get the claim brief done. What is the get the claim brief done. What is the get the claim brief done. What is the simplest way to get this code in front simplest way to get this code in front simplest way to get this code in front of the client? What is the cleanest way of the client? What is the cleanest way of the client? What is the cleanest way to present this PowerPoint? Whatever to present this PowerPoint? Whatever to present this PowerPoint? Whatever your business might be. And you should your business might be. And you should your business might be. And you should have the flexibility, if you're a small have the flexibility, if you're a small have the flexibility, if you're a small business owner, to pick the model array business owner, to pick the model array business owner, to pick the model array that works for you without overwhelming that works for you without overwhelming that works for you without overwhelming your team. And this is where specialists your team. And this is where specialists your team. And this is where specialists can start to play, right? If you're can start to play, right? If you're can start to play, right? If you're constantly making ads or thumbnails or constantly making ads or thumbnails or constantly making ads or thumbnails or mock-ups, it's where names like Flux and mock-ups, it's where names like Flux and mock-ups, it's where names like Flux and Z image and Grok image becomes relevant, Z image and Grok image becomes relevant, Z image and Grok image becomes relevant, right? You don't need to know those right? You don't need to know those right? You don't need to know those names on day one, you just need to know names on day one, you just need to know names on day one, you just need to know the job. I need images, I need the job. I need images, I need the job. I need images, I need references, I need to understand local references, I need to understand local references, I need to understand local control and cheap APIs so I don't control and cheap APIs so I don't control and cheap APIs so I don't overspend on tokens cuz this is such a overspend on tokens cuz this is such a overspend on tokens cuz this is such a heavy part of my business, then you walk heavy part of my business, then you walk heavy part of my business, then you walk into the model name from there. If you into the model name from there. If you into the model name from there. If you work with video, the same logic applies.

work with video, the same logic applies. work with video, the same logic applies. A local video tool like LTX could matter A local video tool like LTX could matter A local video tool like LTX could matter if you want local iterations, a high-end if you want local iterations, a high-end if you want local iterations, a high-end API video model like Seed Dance could API video model like Seed Dance could API video model like Seed Dance could matter when the quality bar is really matter when the quality bar is really matter when the quality bar is really high. Uh a cheap API video route like high. Uh a cheap API video route like high. Uh a cheap API video route like Grok could matter when the point is fast Grok could matter when the point is fast Grok could matter when the point is fast and disposable clips. So the better and disposable clips. So the better and disposable clips. So the better question, again, is to ask what kind of question, again, is to ask what kind of question, again, is to ask what kind of video work you're doing and what's the video work you're doing and what's the video work you're doing and what's the fastest and simplest way to customer fastest and simplest way to customer fastest and simplest way to customer value. The same specialist logic applies value. The same specialist logic applies value. The same specialist logic applies to live information. If the job depends to live information. If the job depends to live information. If the job depends on current web information, try Grok for on current web information, try Grok for on current web information, try Grok for like live X posts. Now X did recently like live X posts. Now X did recently like live X posts. Now X did recently release an API that anybody can plug release an API that anybody can plug release an API that anybody can plug into with any other AI model, but that's into with any other AI model, but that's into with any other AI model, but that's a brand new as the last couple days a brand new as the last couple days a brand new as the last couple days thing and we'll have to see how good it thing and we'll have to see how good it thing and we'll have to see how good it is. But largely, the point here is that is. But largely, the point here is that is. But largely, the point here is that you need to see the customer value you need to see the customer value you need to see the customer value you're looking to create. Look at how a you're looking to create. Look at how a you're looking to create. Look at how a model needs to process files or live web model needs to process files or live web model needs to process files or live web information to create that value and ask information to create that value and ask information to create that value and ask yourself, what is the simplest possible yourself, what is the simplest possible yourself, what is the simplest possible way to get to customer value here? Is it way to get to customer value here? Is it way to get to customer value here? Is it with a daily driver? Is it a normal with a daily driver? Is it a normal with a daily driver? Is it a normal artifact? Is it something GLM 5.2 can artifact? Is it something GLM 5.2 can artifact? Is it something GLM 5.2 can produce with its own native harness? Is produce with its own native harness? Is produce with its own native harness? Is it something that's more complex that I it something that's more complex that I it something that's more complex that I need to wrestle with uh so that I need need to wrestle with uh so that I need need to wrestle with uh so that I need to have Codex involved? Is this to have Codex involved? Is this to have Codex involved? Is this something where the real blocker for me something where the real blocker for me something where the real blocker for me is that my team is not AI fluent enough is that my team is not AI fluent enough is that my team is not AI fluent enough and so I can't use these specialist and so I can't use these specialist and so I can't use these specialist models like Seed Dance for video because models like Seed Dance for video because models like Seed Dance for video because the team isn't ready and I have to just the team isn't ready and I have to just the team isn't ready and I have to just simplify down my staff to just Claude simplify down my staff to just Claude simplify down my staff to just Claude for example because if I expand beyond for example because if I expand beyond for example because if I expand beyond that the team is just going to be that the team is just going to be that the team is just going to be overwhelmed. These are the kinds of overwhelmed. These are the kinds of overwhelmed. These are the kinds of challenges team leaders need to be challenges team leaders need to be challenges team leaders need to be thinking about and talking about is thinking about and talking about is thinking about and talking about is honest trade-offs along the way. And

honest trade-offs along the way. And honest trade-offs along the way. And this is where these company migration this is where these company migration this is where these company migration stories become useful. Lindy is moving stories become useful. Lindy is moving stories become useful. Lindy is moving serious traffic to deep seek because serious traffic to deep seek because serious traffic to deep seek because it's finding it can save money. Cursor it's finding it can save money. Cursor it's finding it can save money. Cursor has been building on Kimmy and moved to has been building on Kimmy and moved to has been building on Kimmy and moved to a pre-trained model again for saving a pre-trained model again for saving a pre-trained model again for saving money. Coinbase is increasing their money. Coinbase is increasing their money. Coinbase is increasing their usage of tokens while decreasing costs usage of tokens while decreasing costs usage of tokens while decreasing costs through smart routing to open source through smart routing to open source through smart routing to open source routers like GLM and Kimmy. routers like GLM and Kimmy. routers like GLM and Kimmy. Shopify and Airbnb are going with Quen Shopify and Airbnb are going with Quen Shopify and Airbnb are going with Quen style routing because they find that style routing because they find that style routing because they find that their queries route there effectively. their queries route there effectively. their queries route there effectively. Microsoft is testing into a deep seek Microsoft is testing into a deep seek Microsoft is testing into a deep seek architecture. So these big companies are architecture. So these big companies are architecture. So these big companies are finding that they need to one, not just finding that they need to one, not just finding that they need to one, not just jump into a one-size-fits-all model and jump into a one-size-fits-all model and jump into a one-size-fits-all model and two, think about what is the straightest two, think about what is the straightest two, think about what is the straightest path to value from their application path to value from their application path to value from their application given a particular kind of intelligence. given a particular kind of intelligence. given a particular kind of intelligence. Don't feel like you're afraid of Claude. Don't feel like you're afraid of Claude. Don't feel like you're afraid of Claude. Don't be afraid of Codex. Those are Don't be afraid of Codex. Those are Don't be afraid of Codex. Those are fantastic models. fantastic models. fantastic models. We need to get to a world where you have We need to get to a world where you have We need to get to a world where you have a much higher dimensional conversation a much higher dimensional conversation a much higher dimensional conversation around model trade-offs. And the point around model trade-offs. And the point around model trade-offs. And the point of this video is to equip you to make of this video is to equip you to make of this video is to equip you to make that trade-off yourself. I can't tell that trade-off yourself. I can't tell that trade-off yourself. I can't tell you always use Quen. Always use Kimmy.

you always use Quen. Always use Kimmy. you always use Quen. Always use Kimmy. Always use GLM. Always use Claude Opus Always use GLM. Always use Claude Opus Always use GLM. Always use Claude Opus 4.8. There's not one simple answer here. 4.8. There's not one simple answer here. 4.8. There's not one simple answer here. What I can tell you is that the route to What I can tell you is that the route to What I can tell you is that the route to get the model right runs through your get the model right runs through your get the model right runs through your job, right? What you need the model to job, right? What you need the model to job, right? What you need the model to do. And it runs through your ability to do. And it runs through your ability to do. And it runs through your ability to get work into and out of that model get work into and out of that model get work into and out of that model efficiently. And that's true whether efficiently. And that's true whether efficiently. And that's true whether you're an individual or whether you're a you're an individual or whether you're a you're an individual or whether you're a team leader or whether you're a company. team leader or whether you're a company. team leader or whether you're a company. I'm just saying use the model that works I'm just saying use the model that works I'm just saying use the model that works for you. Use a model that aligns to what for you. Use a model that aligns to what for you. Use a model that aligns to what you need done. Just to take away, if you need done. Just to take away, if you need done. Just to take away, if it's a middle of the distribution task, it's a middle of the distribution task, it's a middle of the distribution task, which means if it's a fairly simple task which means if it's a fairly simple task which means if it's a fairly simple task for which there are a lot of examples for which there are a lot of examples for which there are a lot of examples online that the model would have seen online that the model would have seen online that the model would have seen before. GLM 5.2 is going to do a great before. GLM 5.2 is going to do a great before. GLM 5.2 is going to do a great job, in some cases better than Claude. job, in some cases better than Claude. job, in some cases better than Claude. If it is a weird, non-standard task that If it is a weird, non-standard task that If it is a weird, non-standard task that requires generalized intelligence, there requires generalized intelligence, there requires generalized intelligence, there is no substitute for a frontier model is no substitute for a frontier model is no substitute for a frontier model right now. You cannot substitute for right now. You cannot substitute for right now. You cannot substitute for Claude or for ChatGPT 5.5 or 5.6 if you Claude or for ChatGPT 5.5 or 5.6 if you Claude or for ChatGPT 5.5 or 5.6 if you can get a hold of it. When you are can get a hold of it. When you are can get a hold of it. When you are tackling a tough generalized task. And tackling a tough generalized task. And tackling a tough generalized task. And the other complexifying factor, as I the other complexifying factor, as I the other complexifying factor, as I keep calling out, is that you need to be keep calling out, is that you need to be keep calling out, is that you need to be thinking how to get work in and out of thinking how to get work in and out of thinking how to get work in and out of this intelligence. That is part of why this intelligence. That is part of why this intelligence. That is part of why I've talked about Gemini less in the I've talked about Gemini less in the I've talked about Gemini less in the last few weeks. Getting work into Gemini last few weeks. Getting work into Gemini last few weeks. Getting work into Gemini and out is something not only I, but and out is something not only I, but and out is something not only I, but many others have called out as many others have called out as many others have called out as unnecessarily difficult. The Gemini unnecessarily difficult. The Gemini unnecessarily difficult. The Gemini harness is not strong for getting work harness is not strong for getting work harness is not strong for getting work out, even though the Gemini intelligence out, even though the Gemini intelligence out, even though the Gemini intelligence is strong. Gemini is a solid model is strong. Gemini is a solid model is strong. Gemini is a solid model without a great harness. And that's

without a great harness. And that's without a great harness. And that's something that I'm seeing a ton of something that I'm seeing a ton of something that I'm seeing a ton of movement on from Chinese open source movement on from Chinese open source movement on from Chinese open source models, and expect more in short order. models, and expect more in short order. models, and expect more in short order. They can see the success that Claude They can see the success that Claude They can see the success that Claude Code is having, the Codex is having. Code is having, the Codex is having. Code is having, the Codex is having. There's a reason they launched GLM 5.2 There's a reason they launched GLM 5.2 There's a reason they launched GLM 5.2 with Z.ai as a harness. Expect more with Z.ai as a harness. Expect more with Z.ai as a harness. Expect more harness work from open source models in harness work from open source models in harness work from open source models in the next couple of months, even as close the next couple of months, even as close the next couple of months, even as close source model makers continue to improve source model makers continue to improve source model makers continue to improve their harnesses. So, the takeaway is their harnesses. So, the takeaway is their harnesses. So, the takeaway is simple. I'm going to give you a few simple. I'm going to give you a few simple. I'm going to give you a few rules of the road here. Do not just copy rules of the road here. Do not just copy rules of the road here. Do not just copy what someone else is doing, and that what someone else is doing, and that what someone else is doing, and that includes me. Don't just copy people. includes me. Don't just copy people. includes me. Don't just copy people. Make sure that you ask yourself how hard Make sure that you ask yourself how hard Make sure that you ask yourself how hard the work is, not just how much work you the work is, not just how much work you the work is, not just how much work you need done. And that's what a lot of the need done. And that's what a lot of the need done. And that's what a lot of the conversation around GLM is about. Is it conversation around GLM is about. Is it conversation around GLM is about. Is it hard work or is it work that you just hard work or is it work that you just hard work or is it work that you just need done? Make sure, number three, that need done? Make sure, number three, that need done? Make sure, number three, that you know how to tell if it's good or you know how to tell if it's good or you know how to tell if it's good or not. Yes, this is evals, but there's not. Yes, this is evals, but there's not. Yes, this is evals, but there's also sniff test, just looking at it and also sniff test, just looking at it and also sniff test, just looking at it and saying, is it actually acceptable? Make saying, is it actually acceptable? Make saying, is it actually acceptable? Make sure that whatever model is available to sure that whatever model is available to sure that whatever model is available to you, whether you work inside a company, you, whether you work inside a company, you, whether you work inside a company, work inside a team, whether you own a work inside a team, whether you own a work inside a team, whether you own a small business, make sure that the model small business, make sure that the model small business, make sure that the model choice itself is not work. And that's choice itself is not work. And that's choice itself is not work. And that's why I keep emphasizing the simplifier of why I keep emphasizing the simplifier of why I keep emphasizing the simplifier of figuring out what the end value is to figuring out what the end value is to figuring out what the end value is to your user and finding the simplest way your user and finding the simplest way your user and finding the simplest way to make that happen. And then just do to make that happen. And then just do to make that happen. And then just do that. And that leads me to number five.

that. And that leads me to number five. that. And that leads me to number five. Don't pick too many models. I'd given Don't pick too many models. I'd given Don't pick too many models. I'd given you the names of like half a dozen or you the names of like half a dozen or you the names of like half a dozen or more models over the course of this more models over the course of this more models over the course of this video. But, it is likely that you don't video. But, it is likely that you don't video. But, it is likely that you don't need that many to get your work done. need that many to get your work done. need that many to get your work done. And to make that easier for you, I would And to make that easier for you, I would And to make that easier for you, I would like you to put that in the comments. like you to put that in the comments. like you to put that in the comments. Put in the comments, this is what I'm Put in the comments, this is what I'm Put in the comments, this is what I'm doing typically, this is the model I'm doing typically, this is the model I'm doing typically, this is the model I'm using. And let's get this conversation using. And let's get this conversation using. And let's get this conversation going as a community. Let's talk amongst going as a community. Let's talk amongst going as a community. Let's talk amongst ourselves about what the best model is. ourselves about what the best model is. ourselves about what the best model is. And I'll pick out some of those comments And I'll pick out some of those comments And I'll pick out some of those comments and use them to call out specific model and use them to call out specific model and use them to call out specific model applications in a future video. All applications in a future video. All applications in a future video. All right, have fun. Subscribe for more right, have fun. Subscribe for more right, have fun. Subscribe for more awesome model picking takes. I hope that awesome model picking takes. I hope that awesome model picking takes. I hope that this was useful to you and help cut this was useful to you and help cut this was useful to you and help cut through the noise. I know there's a ton through the noise. I know there's a ton through the noise. I know there's a ton of noise out there.