Tavily[What is generative web search?]
This is my second use of Tavily. [comparing results for [What is generative web search? site:danielsgriffin.com]](/2023/12/14/comparing-results-for-what-is-generative-web-search-site/) For other syste...
Posts
Filter by tag
hallucinationsocial-search-requestPerplexity-AIcomparing-resultsgenerative-searchprompt engineeringsearch-auditsmicro interactions in searchYou.comspeculative-designGoogle-BardCGTbetter-searchcompetition-in-searchchoice-in-searchgenerative-web-searchknowledge-cutoffsalternative-search-enginesevaluating-results-metasearch-quality-complaintsstanding-queriessearch-engine-optimizationrepository-of-examplesAnthropic-ClaudeCFP-RFPRAGPhinddoubtingadvertising-in-searchseo-for-social-goodOpenAI-ChatGPTpublic-interest-technologyspeculative-classroom-exercisesTavilysearch-user-interfacesgenerative-search-APIfresh-searchautocomplete-in-web-searchfalse-premiseTikTokAndievaluating-search-enginesarticulationsocial-searchdata-poisoningInflection-AI-Piacademic-searchChainForgeautomation biasMeno-Paradox+221 more
A generative search baseline from the You.com Web Search API, a simple prompt, and gpt-3.5-turbo
LOOSE NOTES [comparing results for [What is answer.ai (from Howard & Ries)?]](/2023/12/14/comparing-results-for-what-is-answerai-from-howard-and-ries/) For other systems on this theme, see: - Perplexi...
Tavily[What is answer.ai (from Howard & Ries)?]
Documents testing Tavily's generative search API with the query 'What is answer.ai (from Howard & Ries)?', showing the system failed to locate the specific entity and returned unrelated 'Answer AI' products instead.
Who is going back through prior search interfaces?
Tavily
Documentation about Tavily, a web search and generative search API integrated into LangChain's opengpts, with links to website, playground, API docs, and usage examples.
"We might be returning to the early/pre-Google era of the 1990s where there were multiple search engines"
[What is answer.ai (from Howard & Ries)?]
Comparative evaluation of Perplexity, You.com, Bard, and Bing responses about the newly launched answer.ai R&D lab.
answer.ai & "A new old kind of R&D lab"
"responsibility to test for real world applicability"
"there's pressure for every LLM to have a live web connection"
Commentary on competitive pressure for LLMs to have live web access rather than static knowledge cutoffs.
experimentation in UI (v. training) for disambiguation / clarification
Exploration of UI experimentation versus training approaches for search disambiguation and clarifying questions in AI search assistants.
"Today marks the first year anniversary of the launch of perplexity.ai"
Weblink marking Perplexity AI's first anniversary with founder reflections in thread format.
"The internal name for Deep Search was "Search Harder""
Brief weblink noting Bing's internal codename for Deep Search was 'Search Harder.'
"what do you prefer for live accurate information?"
Weblink polling preference between Perplexity AI and X Grok for live accurate information.
ssr: "Do folks have favorite examples of systematic literature reviews? Better if in HCI, but okay if not."
What questions should we ask when building software?
I've been thinking about these sorts of questions a lot in relation to our current disruption in web search. See some of my musings in Towards “benchmarking” democratization of good search and Who is...
Who is going to try to make web search better?
What organizations are best situated to apply their own resources and promote developer attention and energy to this problem and opportunity?
"Evaluating the Social Impact of Generative AI Systems in Systems and Society"
Solaiman et al. (2023)
"Evaluating Verifiability in Generative Search Engines"
Liu et al. (2023)
"Converting HTML to text" in Liu et al. (2023)
Parsing details in the supplemental materials.