Ask HN: How Perplexity Works?
I am just curious how LLM can scrape the web and access the internet? Also saw Huggingface have a mistral chat with search enabled. How does all of these works?
I am also interested in building such tools.
I am also interested in building such tools.
How can an LLM be trained on realtime data? If not than how does the pplx-70b-online be online?
In my understanding, it's just doing a function call for all the queries using Bing and replying with citations. Nothing new even, Mistral and ChatGPT-4 does it. Also if vector embeddings are being used how can it be scalable?