New Show Hacker News story: Show HN: Web Search Powered by GPT and Bing
Show HN: Web Search Powered by GPT and Bing
14 by aravindsrinivas | 0 comments on Hacker News.
We built a search engine interface on top of OpenAI GPT 3.5 and Microsoft Bing that summarizes and cites top search results in response to natural language questions. By using search results, the AI is able to reference recent news and provide citations for specific facts. Our interface offers concise answers, without having to click through links, scroll past irrelevant content, or read ads. No login is required; no personal data is collected. We believe in the power of combining the intuitive UI of web search with the intelligence of large language models. The search engine does indexing work and interpretation is made by the LLM (a la OpenAI WebGPT https://ift.tt/DQLvW6E ). We are also working on using LLMs to reword queries before searching and to make searches more conversational. Additionally, we are building new features that allow you to curate the result of your query, e.g., by omitting references that are not relevant and expanding the list of references that are relevant. New references could be added either “breadth-first” (include more results from the original query) or “depth-first” (summarize more content from one of the pages in the search results and find related links). Curious what the community thinks, and what features come to mind when you use this interface. Twitter: https://twitter.com/perplexity_ai/status/1600551871554338816 Discord: https://t.co/R4G21AmwQ7
14 by aravindsrinivas | 0 comments on Hacker News.
We built a search engine interface on top of OpenAI GPT 3.5 and Microsoft Bing that summarizes and cites top search results in response to natural language questions. By using search results, the AI is able to reference recent news and provide citations for specific facts. Our interface offers concise answers, without having to click through links, scroll past irrelevant content, or read ads. No login is required; no personal data is collected. We believe in the power of combining the intuitive UI of web search with the intelligence of large language models. The search engine does indexing work and interpretation is made by the LLM (a la OpenAI WebGPT https://ift.tt/DQLvW6E ). We are also working on using LLMs to reword queries before searching and to make searches more conversational. Additionally, we are building new features that allow you to curate the result of your query, e.g., by omitting references that are not relevant and expanding the list of references that are relevant. New references could be added either “breadth-first” (include more results from the original query) or “depth-first” (summarize more content from one of the pages in the search results and find related links). Curious what the community thinks, and what features come to mind when you use this interface. Twitter: https://twitter.com/perplexity_ai/status/1600551871554338816 Discord: https://t.co/R4G21AmwQ7
Comments
Post a Comment