nowfound

AI · December 7, 2022

WS

Web Search Powered by GPT and Bing

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…

Visit perplexity.ai ↗Alternatives

In plain words

Web Search Powered by GPT and Bing is a search engine that combines OpenAI's GPT 3.5 with Microsoft Bing results to answer natural language questions. It summarizes top search results with citations for recent information and specific facts, providing concise answers without requiring users to click through links or view ads. The tool requires no login and collects no personal data, making it useful for anyone seeking quick, sourced answers to questions.

written from the facts on this page · September 2026

From the sources

In the maker’s words, at launch

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://openai.com/blog/webgpt/). 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

More ai this month

the category →
  • I trained a 125M model to autocomplete piano on-device▲598

    I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.

    AI · 17d ago · simedw.com

  • Astute▲585

    Automate your B2B brand going viral, with new media creators

    AI · 18d ago · company-app.joinastute.com

  • Grok Bot▲547

    AI teammates that you can give real work to

    AI · 25d ago · x.ai

  • Needle2: 14MB agentic LLM for phones, wearables, smart home and robots▲537

    Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…

    AI · 26d ago · cactuscompute.com

  • Coldtea.ai▲512

    Make your software self-driving

    AI · 30d ago · coldtea.ai

  • Soloop▲472

    Approval-first Agent OS for solo founders

    AI · 30d ago · soloop.io

Launched alongside, December 2022

the whole month →