Update README.md

README.md

@@ -17,7 +17,9 @@ requirements:
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-This model aims to help developers, especially those with little to no experience in NLP, use our model directly to flag or block users from their platforms. Our model aims to work with any arbitrary language, as long as it is supported by the XLM-R vector space aligner embedder model. #Abuse detection #Toxicity analysis #Obscene language detection
+This model aims to help developers, especially those with little to no experience in NLP, use our model directly to flag or block users from their platforms. Moreover, since our model also knows harmful or unethical comments, it can be used to make AI models, especially when integrated with machines like Robots, provides a last layer of decision to act upon the thoughts. 
+In a nutshell our model assists AI models to better understand whether a thought is ethical or moral, and wheather it should take action on it. Hence making `AI safer for all`. 
+Our model aims to work with any arbitrary language, as long as it is supported by the XLM-R vector space aligner embedder model. #Abuse detection #Toxicity analysis #Obscene language detection #Harm, unethical thought detection.
 
 Langauges supported:
 - Afrikaans