Incorrect or contradicting labels/outputs are provided by the AI and Machine Learning DeepSeek Models
Use Case 1:
The below two features are used as input to DeepSeek.
- current US president
- Current USA President
Ø The first feature i.e., “current US president”, the below label is present by DeepSeek.
Ø The second feature i.e., “Current USA President”, the below label is
present by DeepSeek.
Google Search Results:
The first feature i.e., “current US president” and second feature i.e., “Current USA President”, the below label/output are presented interchangeably:
As of my last update in October 2023, the current President
of the United States is Joe Biden. He assumed office on January 20,
2021. For the most up-to-date information, please verify with a reliable news
source.
OR
The server is busy. Please try again later.
Here the first feature i.e., “current US
president”, the label/output which is present, is contradicting with the second
feature i.e., “Current USA President”, the label/output which is present by
Deepseek.
Summary:
For the
simple features which are being queried, the labels/outputs are contradicting
and, when validated with the Google search, those results are accurate and more
additional & supporting information or data are provided. Hence, we can
safely conclude that incorrect or contradicting labels/outputs are
provided by the AI and Machine Learning Model DeepSeek which we have to cross check
before arriving any conclusion by using AI for outcomes.