Everyoneās Talking About DeepSeek and o3-Mini... But Should You Use Them? Instead of following the hype, letās look at the data.
Hereās what stands out:
š DeepSeek-R1 has completely replaced Claude 3.5 Sonnet. Same SWE-Bench performance, but at a fraction of the price. If youāre still using Claude, youāre paying extra for no real reason.
š° Claude 3.5 Sonnet is insanely expensive. At $15 per million output tokens, it only makes sense for very small coding tasksāotherwise, DeepSeek-R1 is just better.
ā” o3-mini is the best choice for serious AI tasks. ā¢ 200K token context window ā¢ 1,637 tokens per second throughput (fastest on this list) ā¢ Relatively low cost compared to Claude & GPT-4o
For complex AI applications, o3-mini is a no-brainer.
Iām making the switchāo3-mini for everything going forward.
Battle of the AI Models: Which One is Best for Agents?
Iām deep in testing O3-Mini, GPT-4o, DeepSeek-R1, and DeepSeek-V3 to figure out which model is truly the best for AI agents.
To find the winner, Iām stress-testing them against the most common tasks agents need to handle:
š§ Instruction Overload: Can it handle rule-heavy tasks without getting confused or hallucinating? š ļø Tool Call Hell: Can it handle 5 consecutive tool calls, feeding results from one into the next without breaking? š Needle in a Haystack: Can it retrieve precise information from large datasets while staying contextually aware?
So far, one model is dominatingāand Iāll be switching all of my agents over to it going forward.
Iāll share the full results (and the winning model) in my upcoming videoārecording tomorrow, dropping Thursday! Stay tuned.
Which model do you think will win? Drop your guesses below! š
In the middle of stress testing o3-mini and DeepSeek-r1.
o3-mini is winner - it's not even a competition!
I'm testing each model against the most common developer tasks: 1ļøā£ Build a new project from scratch 2ļøā£ Build a new feature in an existing app 3ļøā£ Refactor existing code and generate tests
-
With o3-mini and cursor, I was able to build a ChatGPT replica that allows me to chat with local LLM models in a single shot and everything works like a charm!
On the other hand, DeepSeek-r1 got stuck and only generated a single javascript file. Far from a fully functional website.
Here's the GitHub repo with the prompts so you can replicate the results on your own:
Hey guys! š I'm super excited to share something that's going to change how you interact with your CrewAI setups.
We've just launched a game-changing feature called `crewai chat` that lets you have real conversations with your crews!
In my upcoming video (dropping early this week!), I'll show you exactly how I used this feature to create a professional newsletter in just 5 minutes. Yes, you heard that right - FIVE minutes! š
Here's the magic: I simply chatted with my crew, refining the output until it was perfect. The result? A newsletter that's ready to send to my community.
Check out the actual newsletter my crew generated on Substack in the link below.
Stay tuned for the video release, and in the meantime, let me know what you think of this new feature!
So, if you're creating a Newsletter or Blog Crew where word count matters, give your agent a Word Count Tool (code below š).
Without a Word Count Tool, LLM's give you 800 words max by default because they can't count.
With a Word Count Tool, the agent sees it's not generating enough content and continually rewrites the post until it hits the perfect word count!
-
I bring this up because I'm working on a new YouTube video for y'all that shows you how you can chat with your crews using the new `crewai chat` feature.
In this video, we're going to chat with our Newsletter Crew and continually provide feedback until the Crew generates the perfect newsletter!
Normally, writing a newsletter could take hours.
When you're chatting with a Newsletter Crew, it takes a couple minutes!
I'm super excited for y'all to see this video when it comes out early next week!
Starting a YouTube channel as an AI developer has been one of the most rewarding decisions of my career. Hereās how itās helped me:
š¼ Opened many new job opportunities that helped me 2x my total compensation in just two years. šÆ Allowed me to create courses and coach others, earning tens of thousands of dollars. š¤ Helped me connect with amazing people like you, build credibility, and expand my network.
Iām working on a video to show you exactly how to do this, but I need your help choosing the title: š ļø Option 1: "How to Start an AI Personal Brand" š„ Option 2: "How to Start a YouTube Channel as an AI Developer"
The content will cover the same step-by-step process to help you build your audience, attract opportunities, and grow as an AI developer. I just want to know which title resonates more with you!
If you have any other favorites, please drop in the comments š
(And if you have questions about starting your channel, let me knowāIād love to help!)
I'm wrapping up recording for the Sora masterclass right now, but I wanted to go ahead and share a GPT I created for you guys to help you make AMAZING Sora prompts.
This GPT will help you level up your prompt game from this:
"A beautiful woman sitting outside at a cafe."
To this:
"A beautiful woman sits gracefully outside a quaint cafe in a bustling city at sunset. She sips her coffee while gazing thoughtfully into the distance, surrounded by warm, golden light. The setting is alive with soft chatter and the clinking of glasses, framed by lush greenery and bistro tables. Style: Romantic and cinematic."
In the comments below, I've a link to the GPT so you can try it yourself!
Progress Update: Supabase Vector Store Crash Course
Hey everyone!
Iāve got some cool stuff in the works that I think youāre going to love. š„
Right now, Iām putting together a video thatāll show you how to set up a vector database for free using Supabaseās Postgres vector DB. Iāll walk you through how to build the vector store, save data with embeddings, and make queries to pull relevant info.
This video is part of a bigger series Iāve been working on. In the next one, Iāll teach AI developers how to build an email autoresponder so they can go sell it to their clients. šØ
Hereās the plan: āØ Monitor client emails āØ Store them in a vector DB āØ Automatically generate draft replies
Itās going to be a game-changer for anyone looking to add AI-driven automation to their services. š
The vector DB crash course is dropping soon, so keep an eye out for it! If youāve got any questions or ideas for future videos, hit me up in the comments.
Cheers, Brandon š§āš»š„
P.S.
Be on the look out for this Supabase Vector Store Crash Course coming out later this week!
Today, Iām super excited to share a sneak peek of my latest video, where I walk you through the ultimate AI tech stack for building MVPs (Minimum Viable Products) lightning fast. If youāve been trying to get your AI projects off the ground or want to quickly showcase proof-of-concepts to your clients, youāre in for a treat.
š Why This Stack?
In the upcoming video, I break down a powerful combination of Claude, V0, and Cursor. These tools, when used together, help you build beautiful and functional Next.js MVPs in record time.
The Stack Breakdown: - Claude ā Acts as the brains of the operation, helping you brainstorm ideas, outline, and strategize. Think of Claude as your projectās foundation.
- V0 ā This is your MVP powerhouse. It can crank out Next.js components like a pro and streamline server-side logic to get your app running fast.
- Cursor ā Cursor polishes the details, handles data cleanup, and makes those last-minute tweaks that turn a good MVP into a great one.
āØ Real-World Use Case: Real Estate Offer Letter Generator Let me show you a real-world example. In the video, I walk through how I built a Real Estate Offer Letter Generator in just a couple of hours:
- Input client details and upload documents like conversations and specs.
- Auto-generate offer letters based on uploaded info.
- Tweak values like offer price, export the document, and send to clients with a few clicks.
The coolest part? What usually takes hours was done in minutes using this stack! š²
š·āāļø Building the Pyramid: From Concept to MVP in No Time I like to think of it as constructing a pyramid:
- Base Layer: Claude pulls all your ideas and turns them into a concrete plan.
- Middle Layer: V0 builds out the core components, pages, and server-side logic.
- Top Layer: Cursor polishes the details and handles tweaks to ensure everything runs smoothly.
šÆ Why This Stack Matters for You If youāre a startup founder, this stack lets you get feedback fast. Instead of spending weeks on a product, you can validate concepts in days. š”
For AI freelancers, this is your secret weapon to wow clients. Deliver a functioning proof-of-concept in just hoursāyouāre not just selling ideas, youāre showing whatās possible.
Watch the Sneak Peek š¬ In the video, I show exactly how I built a fully functional app in just a couple of hours. Youāll see the workflow in actionāfrom brainstorming to finished MVPāso you can start building projects faster using the same approach.
24 Hours Left to Lock in Your 50% Pre-Launch Discount on the Fullstack AI Marketing Platform!
Just a quick reminderāthere are only 24 hours left to purchase the Fullstack AI Marketing Platform course at the 50% pre-launch discount! The price goes up from $99 to $149 once the course goes live tomorrow at 6 PM EST.
šØāš» Who is this course for? This course is perfect for beginner to intermediate developers who want to solve real-world problems by building fullstack AI applications. If youāve been looking for a practical course that takes you from identifying a problem to developing a fully functional AI-powered solution, then this is for you!
š§ What Youāll Learn In this course, you'll build an AI marketing platform that automates content generationāsaving creators hours of work by automatically creating social media posts, email campaigns, and more. But hereās the real value: Youāll be mastering core AI automation principles that can be applied to any industry, whether itās real estate, finance, healthcare, or education.
š§ Hereās what youāll actually build and learn: - Create an AI-powered app that automates content creation from video to text, generating social media posts and email campaigns. - Use OpenAI, Whisper, and other AI tools to automate time-consuming workflows. - Deploy a production-ready AI app using Next.js, Vercel, Railway, Typescript, Python, and more. - Master the fullstack development processāfrom coding to deploying and scaling your AI applications.
ā³ The course goes live tomorrow at 6 PM EST and this is your last chance to get it for just $99 before the price jumps to $149.
Join over 150 developers who are already leveling up their fullstack AI skills and turning their ideas into real-world AI solutions!
š Purchase the course now and save 50%! Unlock the AI Course Here
š” Extra Details You Should Know: 30-Day Money-Back Guarantee: If you complete the course and feel it didnāt give you the skills to build and deploy a real AI-powered app, Iāll give you a full refundāno questions asked. If you're not happy, I'm not happy.
Free Coaching Calls: When you purchase the course, youāll also get 6 weeks of live group coaching calls starting on Sunday, September 29th at 12 PM Eastern. These calls will run for six consecutive weeks, where Iāll answer your questions, help workshop your future AI app ideas, and guide you on how to apply everything youāve learned.
Free Modules Already Available: Iāve unlocked the first few modules of the course for free so you can dive in right away. These cover best practices for building real-world AI applications. You can access them in the Skool classroom here:
aiwithbrandon
aiwithbrandon
Everyoneās Talking About DeepSeek and o3-Mini... But Should You Use Them? Instead of following the hype, letās look at the data.
Hereās what stands out:
š DeepSeek-R1 has completely replaced Claude 3.5 Sonnet.
Same SWE-Bench performance, but at a fraction of the price. If youāre still using Claude, youāre paying extra for no real reason.
š° Claude 3.5 Sonnet is insanely expensive.
At $15 per million output tokens, it only makes sense for very small coding tasksāotherwise, DeepSeek-R1 is just better.
ā” o3-mini is the best choice for serious AI tasks.
ā¢ 200K token context window
ā¢ 1,637 tokens per second throughput (fastest on this list)
ā¢ Relatively low cost compared to Claude & GPT-4o
For complex AI applications, o3-mini is a no-brainer.
Iām making the switchāo3-mini for everything going forward.
Whatās your pick?
1 month ago | [YT] | 62
View 12 replies
aiwithbrandon
Battle of the AI Models: Which One is Best for Agents?
Iām deep in testing O3-Mini, GPT-4o, DeepSeek-R1, and DeepSeek-V3 to figure out which model is truly the best for AI agents.
To find the winner, Iām stress-testing them against the most common tasks agents need to handle:
š§ Instruction Overload: Can it handle rule-heavy tasks without getting confused or hallucinating?
š ļø Tool Call Hell: Can it handle 5 consecutive tool calls, feeding results from one into the next without breaking?
š Needle in a Haystack: Can it retrieve precise information from large datasets while staying contextually aware?
So far, one model is dominatingāand Iāll be switching all of my agents over to it going forward.
Iāll share the full results (and the winning model) in my upcoming videoārecording tomorrow, dropping Thursday! Stay tuned.
Which model do you think will win? Drop your guesses below! š
1 month ago | [YT] | 29
View 9 replies
aiwithbrandon
In the middle of stress testing o3-mini and DeepSeek-r1.
o3-mini is winner - it's not even a competition!
I'm testing each model against the most common developer tasks:
1ļøā£ Build a new project from scratch
2ļøā£ Build a new feature in an existing app
3ļøā£ Refactor existing code and generate tests
-
With o3-mini and cursor, I was able to build a ChatGPT replica that allows me to chat with local LLM models in a single shot and everything works like a charm!
On the other hand, DeepSeek-r1 got stuck and only generated a single javascript file. Far from a fully functional website.
Here's the GitHub repo with the prompts so you can replicate the results on your own:
github.com/bhancockio/o3-mini-vs-deepseek-r1
The screenshot below shows the functional app that o3-mini was able to create in a single shot!
I'm still working on the second 2 tasks but right now, there is a clear winner.
I'll keep you posted as I keep testing.
Also, I'll be putting all of this into a YouTube video that will hopefully come out on Monday!
If you have any questions around o3-mini or deepseek-r1, let me know!
I feel like I have a PHD on these models after all the testing I've done over the past 24 hours.
1 month ago | [YT] | 49
View 9 replies
aiwithbrandon
Hey guys! š I'm super excited to share something that's going to change how you interact with your CrewAI setups.
We've just launched a game-changing feature called `crewai chat` that lets you have real conversations with your crews!
In my upcoming video (dropping early this week!), I'll show you exactly how I used this feature to create a professional newsletter in just 5 minutes. Yes, you heard that right - FIVE minutes! š
Here's the magic: I simply chatted with my crew, refining the output until it was perfect. The result? A newsletter that's ready to send to my community.
Check out the actual newsletter my crew generated on Substack in the link below.
Stay tuned for the video release, and in the meantime, let me know what you think of this new feature!
Would you use crewai chat in your workflow?
Cheers,
Brandon Hancock šØāš»š„
open.substack.com/pub/aiwithbrandon/p/4-ways-to-crā¦
3 months ago | [YT] | 21
View 3 replies
aiwithbrandon
Quick āŖ@crewAIIncā¬ and LLM Tip:
LLMs are lazy and struggle with word count.
So, if you're creating a Newsletter or Blog Crew where word count matters, give your agent a Word Count Tool (code below š).
Without a Word Count Tool, LLM's give you 800 words max by default because they can't count.
With a Word Count Tool, the agent sees it's not generating enough content and continually rewrites the post until it hits the perfect word count!
-
I bring this up because I'm working on a new YouTube video for y'all that shows you how you can chat with your crews using the new `crewai chat` feature.
In this video, we're going to chat with our Newsletter Crew and continually provide feedback until the Crew generates the perfect newsletter!
Normally, writing a newsletter could take hours.
When you're chatting with a Newsletter Crew, it takes a couple minutes!
I'm super excited for y'all to see this video when it comes out early next week!
3 months ago | [YT] | 45
View 5 replies
aiwithbrandon
Starting a YouTube channel as an AI developer has been one of the most rewarding decisions of my career.
Hereās how itās helped me:
š¼ Opened many new job opportunities that helped me 2x my total compensation in just two years.
šÆ Allowed me to create courses and coach others, earning tens of thousands of dollars.
š¤ Helped me connect with amazing people like you, build credibility, and expand my network.
And hereās how it could help you:
š Land better jobs with your channel acting as an online rĆ©sumĆ©.
š Kickstart a career in freelancing or AI consulting by showcasing your portfolio.
š” Test and validate app ideas with your audience before committing months to development.
Iām working on a video to show you exactly how to do this, but I need your help choosing the title:
š ļø Option 1: "How to Start an AI Personal Brand"
š„ Option 2: "How to Start a YouTube Channel as an AI Developer"
The content will cover the same step-by-step process to help you build your audience, attract opportunities, and grow as an AI developer. I just want to know which title resonates more with you!
If you have any other favorites, please drop in the comments š
(And if you have questions about starting your channel, let me knowāIād love to help!)
3 months ago | [YT] | 7
View 13 replies
aiwithbrandon
I'm wrapping up recording for the Sora masterclass right now, but I wanted to go ahead and share a GPT I created for you guys to help you make AMAZING Sora prompts.
This GPT will help you level up your prompt game from this:
"A beautiful woman sitting outside at a cafe."
To this:
"A beautiful woman sits gracefully outside a quaint cafe in a bustling city at sunset. She sips her coffee while gazing thoughtfully into the distance, surrounded by warm, golden light. The setting is alive with soft chatter and the clinking of glasses, framed by lush greenery and bistro tables. Style: Romantic and cinematic."
In the comments below, I've a link to the GPT so you can try it yourself!
4 months ago | [YT] | 16
View 1 reply
aiwithbrandon
Progress Update: Supabase Vector Store Crash Course
Hey everyone!
Iāve got some cool stuff in the works that I think youāre going to love. š„
Right now, Iām putting together a video thatāll show you how to set up a vector database for free using Supabaseās Postgres vector DB. Iāll walk you through how to build the vector store, save data with embeddings, and make queries to pull relevant info.
This video is part of a bigger series Iāve been working on. In the next one, Iāll teach AI developers how to build an email autoresponder so they can go sell it to their clients. šØ
Hereās the plan:
āØ Monitor client emails
āØ Store them in a vector DB
āØ Automatically generate draft replies
Itās going to be a game-changer for anyone looking to add AI-driven automation to their services. š
The vector DB crash course is dropping soon, so keep an eye out for it! If youāve got any questions or ideas for future videos, hit me up in the comments.
Cheers,
Brandon š§āš»š„
P.S.
Be on the look out for this Supabase Vector Store Crash Course coming out later this week!
6 months ago | [YT] | 50
View 6 replies
aiwithbrandon
Hey everyone! š
Today, Iām super excited to share a sneak peek of my latest video, where I walk you through the ultimate AI tech stack for building MVPs (Minimum Viable Products) lightning fast. If youāve been trying to get your AI projects off the ground or want to quickly showcase proof-of-concepts to your clients, youāre in for a treat.
š Why This Stack?
In the upcoming video, I break down a powerful combination of Claude, V0, and Cursor. These tools, when used together, help you build beautiful and functional Next.js MVPs in record time.
The Stack Breakdown:
- Claude ā Acts as the brains of the operation, helping you brainstorm ideas, outline, and strategize. Think of Claude as your projectās foundation.
- V0 ā This is your MVP powerhouse. It can crank out Next.js components like a pro and streamline server-side logic to get your app running fast.
- Cursor ā Cursor polishes the details, handles data cleanup, and makes those last-minute tweaks that turn a good MVP into a great one.
āØ Real-World Use Case: Real Estate Offer Letter Generator
Let me show you a real-world example. In the video, I walk through how I built a Real Estate Offer Letter Generator in just a couple of hours:
- Input client details and upload documents like conversations and specs.
- Auto-generate offer letters based on uploaded info.
- Tweak values like offer price, export the document, and send to clients with a few clicks.
The coolest part? What usually takes hours was done in minutes using this stack! š²
š·āāļø Building the Pyramid: From Concept to MVP in No Time
I like to think of it as constructing a pyramid:
- Base Layer: Claude pulls all your ideas and turns them into a concrete plan.
- Middle Layer: V0 builds out the core components, pages, and server-side logic.
- Top Layer: Cursor polishes the details and handles tweaks to ensure everything runs smoothly.
šÆ Why This Stack Matters for You
If youāre a startup founder, this stack lets you get feedback fast. Instead of spending weeks on a product, you can validate concepts in days. š”
For AI freelancers, this is your secret weapon to wow clients. Deliver a functioning proof-of-concept in just hoursāyouāre not just selling ideas, youāre showing whatās possible.
Watch the Sneak Peek š¬
In the video, I show exactly how I built a fully functional app in just a couple of hours. Youāll see the workflow in actionāfrom brainstorming to finished MVPāso you can start building projects faster using the same approach.
6 months ago | [YT] | 0
View 0 replies
aiwithbrandon
24 Hours Left to Lock in Your 50% Pre-Launch Discount on the Fullstack AI Marketing Platform!
Just a quick reminderāthere are only 24 hours left to purchase the Fullstack AI Marketing Platform course at the 50% pre-launch discount! The price goes up from $99 to $149 once the course goes live tomorrow at 6 PM EST.
šØāš» Who is this course for? This course is perfect for beginner to intermediate developers who want to solve real-world problems by building fullstack AI applications. If youāve been looking for a practical course that takes you from identifying a problem to developing a fully functional AI-powered solution, then this is for you!
š§ What Youāll Learn In this course, you'll build an AI marketing platform that automates content generationāsaving creators hours of work by automatically creating social media posts, email campaigns, and more.
But hereās the real value: Youāll be mastering core AI automation principles that can be applied to any industry, whether itās real estate, finance, healthcare, or education.
š§ Hereās what youāll actually build and learn:
- Create an AI-powered app that automates content creation from video to text, generating social media posts and email campaigns.
- Use OpenAI, Whisper, and other AI tools to automate time-consuming workflows.
- Deploy a production-ready AI app using Next.js, Vercel, Railway, Typescript, Python, and more.
- Master the fullstack development processāfrom coding to deploying and scaling your AI applications.
ā³ The course goes live tomorrow at 6 PM EST and this is your last chance to get it for just $99 before the price jumps to $149.
Join over 150 developers who are already leveling up their fullstack AI skills and turning their ideas into real-world AI solutions!
š Purchase the course now and save 50%! Unlock the AI Course Here
www.skool.com/ai-developer-accelerator/classroom
š” Extra Details You Should Know:
30-Day Money-Back Guarantee: If you complete the course and feel it didnāt give you the skills to build and deploy a real AI-powered app, Iāll give you a full refundāno questions asked. If you're not happy, I'm not happy.
Free Coaching Calls: When you purchase the course, youāll also get 6 weeks of live group coaching calls starting on Sunday, September 29th at 12 PM Eastern. These calls will run for six consecutive weeks, where Iāll answer your questions, help workshop your future AI app ideas, and guide you on how to apply everything youāve learned.
Free Modules Already Available: Iāve unlocked the first few modules of the course for free so you can dive in right away. These cover best practices for building real-world AI applications. You can access them in the Skool classroom here:
www.skool.com/ai-developer-accelerator/classroom/0ā¦
If you have any questions, feel free to drop a comment below or email me at directly brandon@brandonhancock.io
Cheers,
Brandon š§āš»
7 months ago | [YT] | 30
View 10 replies
Load more