Artificial intelligence (AI) is developing rapidly, and the Chinese-developed DeepSeek AI chatbot is one of the latest technologies making waves. There are many advantages to DeepSeek’s fast and detailed response, but there are also some disadvantages that make it probably not the AI ​​tool you’re aiming for.

What is DeepSeek?

DeepSeek is a new AI technology developed by a Chinese technology company. Its flagship model, DeepSeek-V3, uses a unique Mixture-of-Experts (MoE) architecture. Think of it as a “group” of specialized AI systems, where only the most relevant experts are “enabled” to handle specific tasks, where each “expert” is a network specialized neurons.

DeepSeek claims that its LLM V3 was trained on a whopping 14.8 trillion tokens, with 1 million tokens equivalent to about 750,000 words. DeepSeek V3 is also a massive LLM in general, with 671 billion parameters across its entire MoE architecture, with 37 billion of those parameters enabled per token. That means each reminder has massive processing power behind it, with faster and more efficient performance.

Furthermore, it is an open source AI model, meaning anyone can explore, test, and build for free. This sets it apart from competitors that keep their models behind paywalls.

Check out DeepSeek

To see how DeepSeek-V3 performs, test it on three real-life tasks: creative writing, coding assistance, and productivity-related work. Its performance demonstrates both versatility and raw power, with a few minor hiccups along the way.

Task 1: Write a description of a fictional character

The author of the article asked DeepSeek to write a detailed description of a fictional character: A rebel queen leading a resistance against an evil empire. The output is very vivid and engaging.

Task 2: Debug a JavaScript function

Test DeepSeek’s programming skills by feeding it a faulty JavaScript function that calculates the factorial of a number. Here is the error code provided:

​​​​function factorial(n) {  
if (n = 1) {  
return 1;  
}  
return n * factorial(n - 1);  
} 

DeepSeek immediately discovered the problem: The equal sign (=) in the condition caused a logic error. It provided the corrected code and also explained the issue:

This fix works perfectly and its explanation is clear enough for a JavaScript novice to understand.

Task 3: Productivity – Create a meeting schedule

To test productivity, ask DeepSeek to draft a brief agenda for a project team meeting about a new product launch.

DeepSeek excels at creative writing, programming, and productivity-related tasks, delivering polished output across the board. As with any AI tool, it is important to consider the accuracy of the output, especially when accuracy is a key factor.

Advantages, disadvantages and things worth noting in DeepSeek

After putting DeepSeek to the test, several strengths and weaknesses of this AI model became prominent. It also surprised us in some unexpected ways.

DeepSeek handles multiple tasks with ease. From creating vibrant compositions to debugging complex code, it has proven to be as versatile as leading AI models. Its Mixture-of-Experts architecture is as expected, making DeepSeek fast without affecting output quality. For example, it generates detailed outputs such as character descriptions or meeting agendas in just a few seconds. DeepSeek adjusts its tone and style with ease. Whether working on official documents or composing, it can tailor its responses to the task.

Like many other AI models, DeepSeek sometimes provides inaccurate or incomplete information, especially when asked about in-depth or very specific topics. For example, in a test related to historical events, it confidently gives an incorrect answer.

Although DeepSeek is open source, its support documentation and tutorials are not as robust as tools like GPT-4, making it difficult for new users to maximize the model’s potential. Due to its Chinese origin, some users may be concerned about how their data is processed or stored. While there is no evidence that their data was misused, these concerns are worth considering for sensitive tasks (like any AI chatbot!).

Perhaps most surprising is that for a model developed in China, DeepSeek has demonstrated incredible fluency in global cultures and perspectives. It shows a deep understanding of topics ranging from European literature to African history. DeepSeek’s creativity is another unexpected strength. When asked to describe a character, it not only gives a description but also creates context around that character and how that character relates to other characters.