Why DeepSeek R1 is the Future of AI: A Game-Changer You Need to Try
DeepSeek R1: The Free AI Model That’s Shaking Up the Tech World
Hey friends, In case you missed my previous blog post, here is another. DeepSeek R1 has been making waves in the AI and tech scene. It's an open-source AI model that was apparently developed for less than $6 million—a fraction of the billions of dollars spent by OpenAI and Google, for example, to create their AI models.
The good news for all of us is that DeepSeek is free to use, and it has shot up to the most downloaded app on the App Store, surpassing ChatGPT within days. It's now one of the most advanced free and open-source AI models we can use.
I've been playing around with DeepSeek R1 for a couple of days, and I have to say it's game-changing, but it's not without its flaws. So let's run through what DeepSeek R1 is capable of and see what the fuss is all about.
Click here to visit DeepSeek R1.
Why DeepSeek R1 is Making Waves
One of the main reasons why DeepSeek R1 is so hyped is because it doesn't rely on expensive human-labeled datasets or supervised fine-tuning, which is how most AI models are trained—and it costs millions, if not billions.
Instead, DeepSeek R1 uses a self-reinforced learning method without the need for human supervision and effort. You can think of supervised fine-tuning like teaching a child to cook by writing up a long and precise recipe and then showing them step by step, while reinforcement learning is allowing the child to sort of experiment in the kitchen and gently guiding them when dishes don't turn out well. So they're learning through trial and error, and that's exactly how DeepSeek was trained.
The benchmark results are incredible. On the AIM 2024 mathematics benchmark, DeepSeek achieves 71% accuracy, while GB1 Mini achieves 63.6% accuracy. And on the Math 500 benchmark, it beat both 01 Mini and 01 0912. However, it performs worse on coding tasks in CodeForce and LiveCode benchmarks.
But, of course, there's much more to benchmarks, so let's dive into the next part of this blog post.
Getting Started with DeepSeek R1
So let’s jump onto DeepSeek.com. Here’s where you can create an account, or you can go ahead and download the app on your phone. But currently, their servers are super slow because of the crazy demand, so I recommend avoiding signing up with an email. You’ll probably be waiting forever for an email verification code, so I suggest logging in directly through a Google account.
Once you’re in, toggle on the DeepSeek R1 model here. It’s an advanced reasoning model similar to GPT’s 01 model, but without GPT’s 01’s 50-message-per-week restriction. And also, R1 is able to work alongside internet search—toggle this toggle right here simultaneously, something I believe 01 still can’t do yet.
Key Features of DeepSeek R1
R1 model uses the Chain of Thought prompting approach, which basically encourages the AI model to break down the reasoning into simple, easy-to-understand steps. This isn’t new, but DeepSeek R1 does this really well.
Let’s use this simple math problem as an example. The first part here is the problem to solve, and the second is the prompt that I’ve added to show its Chain of Thought. So specifically, let’s solve this step by step. For each step, explain your thinking and show your calculations.
Hitting enter, you can see DeepSeek thinking and reasoning with itself. And this is what makes R1 different—it transparently reasons through each step individually and figures it out in the same response in real time. Whereas GPT can often be sort of clinical and political, I found DeepSeek R1 to be direct but also great at showing you the reasoning. You can also extract the reasoning and send it to other AI models too, something that’s unique to DeepSeek R1.
The other cool thing is how DeepSeek R1 solves hallucinations. Hallucinations is a term to describe when AI gives you an incorrect answer, and it’s a big challenge with current AI models. But I’ve noticed that R1 is particularly good at understanding why it hallucinates, almost as if it’s truly self-aware, and then it also corrects itself.
For example, I started recording a specific clip when I noticed that it gave me an incorrect answer to the vague question of what happened to Hershey’s in 1998. It says Hershey’s launched Almond Kisses in 1988, when in reality they were actually launched in 1990. So I pointed out the mistake and asked why it made the mistake. Because of its Chain of Thought approach, it’s fascinating to see it run a search on this mistake, confirm why it made a mistake, and then correct itself here.
Compared to other AI models, DeepSeek R1 thinks way more naturally, almost human-like, and elaborates on its mistakes clearly. So I highly recommend challenging R1 when it hallucinates and giving this a go yourself.
Performance Insights
It does seem to be slower though than ChatGPT 4.0, especially when it comes to coding tasks. I’ve been playing around with creating games on DeepSeek. For example, if we ask it to create a Tetris game and then take the Python code and run it in HTML, it takes longer than it would in ChatGPT 4.0 before you can preview the game right from the chat.
So, if you have coding tasks, GPT 4.0 and particularly Claude 3.5 still do a better job overall and will help remove the need to debug as a coder. But if you’re looking for a free option or an open-source option, R1 here is definitely the way to go currently and worth checking out.
Based on my short time with R1, I feel like DeepSeek was probably trained on GPT-4 generated data. The responses on both models are easily similar.
Privacy and Accessibility
If you’re concerned about privacy but still want to leverage DeepSeek R1, you can actually run it locally because it’s open source. You can download and use the AMA app to run this R1 model on a local server so all your questions and interactions remain completely private rather than on the cloud.
But it is a very large model, so you’ll need a beast of a setup to run its full R1 model locally. It’s roughly 1,300 GB of VRAM that you’ll need to run it fully. However, there are distilled LLM versions of R1 that run on a single GPU.
Comparison to Other AI Models
Based on my short time with R1, I feel like DeepSeek was probably trained on GPT-4 generated data. The responses on both models are easily similar.
Compared to other AI models, DeepSeek R1 thinks way more naturally, almost human-like, and elaborates on its mistakes clearly. However, when it comes to coding tasks, GPT-4 and Claude 3.5 still perform better and reduce the need for debugging.
That's to said, if you’re looking for a free option or an open-source alternative, R1 is definitely the best choice currently and worth exploring further.
Conclusion
Here’s my first look at DeepSeek R1. Clearly, some incredible things are happening in the AI space. When I began using DeepSeek, I was skeptical, but I quickly realized it’s truly something special. Considering its low cost to build and availability as a free-to-use model, it's an exciting time in the AI world.
I’m eager to see how others, like OpenAI, respond to DeepSeek. If you’ve made it to the end of this blog post, comment the code word "R1," and I’ll give it a like for making it this far. And as always, thanks for reading, stay tune to another engaging blog post!
