Tavily[What is generative web search?]

    .include_domains(danielsgriffin.com)

    December 14th, 2023

    Pretty good but not a particularly difficulty query. I do appreciate having my website in the index.

    A wild line: “It’s worth noting that the information provided is based on the given data and sources available up to 14/12/2023.”

    Generated in the Tavily Playground: Settings:

    • Search Depth: basic
    • Limit Sources: 5
    • Include Answer: [x]
    • Include Domains: danielsgriffin.com
    Tavily[What is generative web search?].include_domains(danielsgriffin.com)

    “Generative web search refers to the use of generative AI systems for conducting web searches. These systems are designed to generate search results and responses based on user queries. They can utilize various models and algorithms to generate the search results. Funding for the development and operation of generative web search systems can come from different sources, including individual ownership, usage fees, public funding, philanthropic gifting, crowdsourced models, routing funding through other tools, and advertising-based models.

    There are ongoing efforts to improve generative web search and evaluate its effectiveness. Evaluation of generative search can involve comparing different platforms or tools, analyzing the generated text and links, assessing speed and user interface features, and benchmarking the democratization of good search. Various organizations and developers are exploring ways to make web search better and promote alternative models of search, leveraging large language models and disruptive energy in the field.’s worth noting that the information provided is based on the given data and sources available up to 14/12/2023.”


    Full json response:

    
    {
        "query": "What is generative web search?",
        "follow_up_questions": null,
        "answer": "Generative web search refers to the use of generative AI systems for conducting web searches. These systems are designed to generate search results and responses based on user queries. They can utilize various models and algorithms to generate the search results. Funding for the development and operation of generative web search systems can come from different sources, including individual ownership, usage fees, public funding, philanthropic gifting, crowdsourced models, routing funding through other tools, and advertising-based models.\n\nThere are ongoing efforts to improve generative web search and evaluate its effectiveness. Evaluation of generative search can involve comparing different platforms or tools, analyzing the generated text and links, assessing speed and user interface features, and benchmarking the democratization of good search. Various organizations and developers are exploring ways to make web search better and promote alternative models of search, leveraging large language models and disruptive energy in the field.\n\nIt's worth noting that the information provided is based on the given data and sources available up to 14/12/2023.",
        "images": null,
        "results": [
            {
                "title": "Who is going to try to make web search better?",
                "url": "https://danielsgriffin.com/2023/12/05/who-is-going-to-try-to-make-web-search-better/",
                "content": "Search is a mess, it seems either broken or bought or shaped by a behemoth. But sparks of disruption in the energy around large language models (LLMs) have helped some to imagine alternative models of search. What organizations are best situated to apply their own resources and promote developer attention and energy to this problem and opportunity?",
                "score": 0.97179,
                "raw_content": null
            },
            {
                "title": "Aggressively Imagining Funding Models for Generative Web Search",
                "url": "https://danielsgriffin.com/pposts/2023/11/01/aggressively-imagining-funding-models-for-generative-web-search/",
                "content": "There are several potential models for funding the development and ongoing operations of generative AI systems for web search, including individually-owned systems, usage fees, public funding, philanthropic gifting, crowdsourced models, routing funding through other tools, and advertising-based models. Each approach has tradeoffs around factors ...",
                "score": 0.95924,
                "raw_content": null
            },
            {
                "title": "The Need for ChainForge-like Tools in Evaluating Generative Web Search ...",
                "url": "https://danielsgriffin.com/pposts/2023/08/31/chainforge-for-generative-search/",
                "content": "When I'm comparing different generative web search platforms or tools I'm taking screenshots, copying the text responses, and/or sharing links to the results. 2 I'm looking at the generated text and links and other elements of the search experience, including speed and UI features. What could evaluation look like for generative search?",
                "score": 0.95736,
                "raw_content": null
            },
            {
                "title": "Towards \"benchmarking\" democratization of good search.",
                "url": "https://danielsgriffin.com/2023/12/04/towards-benchmarking-democratization-of-good-search/",
                "content": "Generative web search systems are designed to wrap around different base models. Such systems, like You.com or Perplexity AI, are often built atop OpenAI's APIs (sometimes through Microsoft) but have added support for other private and open-source models as well as fine-tuned their own. Such systems have also built atop various sources of web ...",
                "score": 0.95697,
                "raw_content": null
            },
            {
                "title": "A generative search baseline from the You.com Web Search API, a simple ...",
                "url": "https://danielsgriffin.com/2023/12/13/a-generative-search-baseline-from-the-youcom-web-search-api-a-simple-prompt-and-gpt-35-turbo/",
                "content": "- A generative search baseline from the You.com Web Search API, a simple prompt, and gpt-3.5-turbo - changes 2023-12-13 - Tavily[What is answer.ai (from Howard & Ries)?] - Who is going back through prior search interfaces? - Tavily - \"We might be returning to the early/pre-Google era of the 1990s where there were multiple search engines\"",
                "score": 0.94078,
                "raw_content": null
            }
        ],
        "response_time": 3.49
    }