Thanks Bret. I tried out purplexity and I have this slight fear that it sources the wikipedia for too many queries. It seems as if wikipedia is the go to source for this tool. But as you said, it did not give too many hazy or outrightly wrong answers. In fact, I asked a few questions about Sanskrit verse forms and it gave right answers. I somehow do not see purplexity as conversational to warrant a comparison with ChatGPT. ChatGPT is extremely conversational. As in, when I asked if he can help me with search, the bot said he is not connected to the internet and listed out all his limitations. It sounded like a conversation. Whereas purplexity is yet to give such a cohesive answer, although I must admit that I have not tested it extensively as I write this. Thanks for leading me to this wonderful tool.
Great points. I agree, it is not as conversational as ChatGPT. It does provide conversational responses to queries and does retain context through a thread, but the alignment around chat is not a concrete. It is more search engine with some conversational features.
As to Wikipedia, this was a problem with voice assistants. They found it easiest to just go with Wikipedia because the data is fairly similar across pages. The first two sentences typically have a similar structure. So, the easiest option was just to source Wikipedia.
However, with Perpexity, I am seeing a lot more sources from web pages. Granted it generally lifts exact or nearly exact statements from those pages much like you find with Google's answer boxes. ChatGPT and other Instruct models do a much better job synthesizing information from across sources.
Thanks Bret. I tried out purplexity and I have this slight fear that it sources the wikipedia for too many queries. It seems as if wikipedia is the go to source for this tool. But as you said, it did not give too many hazy or outrightly wrong answers. In fact, I asked a few questions about Sanskrit verse forms and it gave right answers. I somehow do not see purplexity as conversational to warrant a comparison with ChatGPT. ChatGPT is extremely conversational. As in, when I asked if he can help me with search, the bot said he is not connected to the internet and listed out all his limitations. It sounded like a conversation. Whereas purplexity is yet to give such a cohesive answer, although I must admit that I have not tested it extensively as I write this. Thanks for leading me to this wonderful tool.
Great points. I agree, it is not as conversational as ChatGPT. It does provide conversational responses to queries and does retain context through a thread, but the alignment around chat is not a concrete. It is more search engine with some conversational features.
As to Wikipedia, this was a problem with voice assistants. They found it easiest to just go with Wikipedia because the data is fairly similar across pages. The first two sentences typically have a similar structure. So, the easiest option was just to source Wikipedia.
However, with Perpexity, I am seeing a lot more sources from web pages. Granted it generally lifts exact or nearly exact statements from those pages much like you find with Google's answer boxes. ChatGPT and other Instruct models do a much better job synthesizing information from across sources.