
- Deepseek has one of the very largest Nvidia clusters in Asia
- Deepseek and Chat GPT training date data is the same [June 2024]
- Deepseek performs and makes the same errors as ChatGPT 3/4
- The Hedge fund that owns Deepseek regularly shorts stocks
Deepseek Cluster is huge
DeepSeek’s cluster, reportedly around 50,000 NVIDIA GPUs, ranks as one of the largest GPU clusters in Asia. Here’s how it compares with other major GPU clusters in the region:
- DeepSeek Cluster (China)
- Size: Approximately 50,000 NVIDIA GPUs.
- Colossus Cluster (Asia, exact owner/location undisclosed):
- Size: Over 100,000 NVIDIA H100 GPUs, making it the largest GPU cluster globally.
- GreenNode Cluster (Thailand):
- Size: 1,024 NVIDIA H100 GPUs (smaller than DeepSeek’s cluster but significant for Southeast Asia).
- NSTDA Supercomputer (Thailand):
- Size: 704 NVIDIA A100 GPUs.
- China’s National Supercomputers:
- Tianhe-2A: Uses Matrix-2000 accelerators alongside CPUs, but the GPU count is less than 50,000.
Relative Position:
- DeepSeek’s cluster is one of the largest in Asia specifically for NVIDIA GPU-based AI applications.
- While it is smaller than Colossus, it outpaces most other clusters in the region in terms of GPU count and computing capacity.
- This positions DeepSeek among the leading AI hardware infrastructures in Asia, focused on cutting-edge AI development.
Same Training date cut-off of June 2024
I asked both “what is today’s news“
DeepSeek: As of my last update in July 2024, I don’t have real-time information. For today’s news, please check reliable news websites, apps, or platforms like BBC, CNN, Reuters, or others. If you want real-time info, please enable the Internet search feature at the bottom of the dialog box.
ChatGPT: My training data cutoff is June 2024. However, I can access and retrieve up-to-date information from the web when needed, ensuring my responses are current. If you’d like, I can help with the latest information!
Same Mistake as GPT 5 – The cup and ball Question
I asked – I put a small ball on a table and put a cup over it. I pick the cup up and then look inside it – what do I see
ChatGPT 4: When you lift the cup from the table where you placed the small ball and look inside, you should see the ball inside the cup, unless it has been moved or there’s some trick involved
Deepseek R1: IS WRONG ”When you pick up the cup and look inside, you will see the small ball that you originally placed on the table and covered with the cup. The ball should still be there, assuming:
- The cup was placed firmly over the ball, preventing it from rolling away.
- The cup was lifted straight up without tilting or shaking it, which could cause the ball to move or fall out.
If everything was done carefully, the ball will remain inside the cup when you lift it and look inside.”
Chat GPT 4o gets it right : If you place a cup over a ball on a table and then lift the cup to look inside it, the ball will no longer be inside the cup—it will still be sitting on the table where it was originally placed. The cup only “contains” the ball while it’s covering it, but once lifted, the ball stays put on the table.
Claude does even better and notably different as you would expect from a different algo and training data
Well, there are two possibilities:
- If the ball somehow stuck to or adhered to the inside of the cup when you lifted it, you would see the ball inside the cup.
- More likely, since most small balls don’t stick to cups, you would see just the empty inside of the cup, as the ball would have remained on the table when you lifted the cup.
Without knowing what kind of ball and cup we’re talking about and whether there are any special conditions involved, the second scenario seems most probable – you’d likely see an empty cup while the ball sits on the table where you originally placed it.
What actually happened when you tried this?