The new DeepSeek R1 model from China launched last week. If you’re into AI or even into technology more broadly, it was hard to miss the news. Everyone was talking about it. But it’s not just that. It’s the way everyone was talking about it. I was left with the impression that DeepSeek is going to drive a stake through the heart of OpenAI and Anthropic.
But we all know how the internet works. Whenever some shiny new AI toy is released there’s always a lot of chatter and excitement. Sometimes it lives up to the hype. Other times it fizzles out and turns into a historical .
Where will DeepSeek end up?
Only time will tell. But if you’re curious about it and want to get an overview of what it’s capable of without testing it yourself, then you’re in the right place. After reading about ten articles on how amazing it is, I decided to take it for a spin. Keep reading to learn more about the experiments I ran and what I discovered about DeepSeek’s strengths and limitations.
It doesn’t look like you were actually using the R1 model for DeepSeek. It may have been more fair to compare GPT-4o to DeepSeek V3 and GPT-o1 to DeepSeek R1.
I personally found that DeepSeek R1 appears to perform much worse than GPT-4o. I think this is sometimes because if you hit a problem where it’s doing something wrong it gets even better at it!
I should also mention that ChatGPT did to me the same thing where it weirdly deleted the response and prompt after the message on a certain topic. There’s potentially the same censorship here it’s just on different things though it might have also been a glitch.
Great article by the way 🫡
What about the Deepthink(R1) feature ??
I really enjoyed this article—it gives such a well-rounded and insightful look at the new DeepSeek R1 model! The detailed testing and comparisons with GPT-01 and Claude 3.5 Sonnet make it so easy to understand how DeepSeek stacks up. I especially appreciate the real-world examples and the methodical approach.
It’s a fantastic read for anyone interested in the latest AI advancements. Big thanks to Martin Dubovic for putting together such a thorough and engaging analysis!
Thanks for your kind words Mike and for taking the time to leave a comment. I appreciate it and I’m glad you enjoyed the read.