Topic

Search

Everything filed under Search, newest first.

Showing 1–14 of 14 articles

  • The Brave Search API now accepts agentic payments via the x402 protocol

    Brave announces that its Search API now supports pay-as-you-go agentic payments via the open x402 protocol: agents pay per request in USDC on Base (about $0.005 per query) with no account or API key, using a 402 Payment Required challenge and signed payment retry.

    Announcement · ai · ai-agents · search · payments

    2 min · 419 words

  • How Google’s anti-scraping move became our problem (and how we solved it in a user-first way)

    Brave explains how Google's GOTO redirects pushed scrapers toward Brave Search, and its answer: a brave.com/go URL cloaking scheme built on partially oblivious pseudorandom functions that makes bot scraping more expensive while Brave still never learns which result a user clicked.

    Blog post · search · privacy · security · cryptography

    6 min · 1,313 words

  • Google's AI Overviews cut clicks to websites by 40%

    RevScope reviews a randomized experiment showing Google AI Overviews cut clicks to outside websites by about 40%, notes Overviews now appear on over half of tracked US keywords, and finds GEO looks mostly like SEO plus third-party presence and quotable pages.

    Research · seo · search · ai

    17 min · 3,972 words

  • Education Shouldn't Be Held for Ransom

    An open letter from Kagi's Kevin Elgan criticising Google's plan to switch off Google Search along with AI tools by default for K-12 Workspace for Education accounts, arguing schools should not have to accept AI to get search, and pitching Kagi's AI-off-by-default search for schools.

    Opinion · education · search · ai

    6 min · 1,310 words

  • Zombie Stats: Where the Numbers AI Quotes Come From

    Trakkr Research asked ChatGPT, Perplexity, Gemini, Claude and Google AI Overviews 200 questions that call for a number, then followed each citation back toward its original source, finding that the page AI cites is often a roundup or blog that copied the original, sometimes with an older figure.

    Research · ai · research · search

    12 min · 2,861 words

  • Do We Still Have to Denormalize? Have Your Schema and Search It Too

    Stu Hood explains how ParadeDB handles relevance-sorted search and facet aggregations across joined Postgres tables, so teams no longer need to denormalize their schema into a separate search index, with benchmarks against plain Postgres.

    Blog post · databases · search · performance

    14 min · 3,118 words

  • Bag of Decisions Reranker

    Doug Turnbull experiments with treating search queries as a "bag of decisions": an LLM generates query-specific yes/no relevance questions, Jev answers them per document, and the results are combined into a reranker, with code and evaluation results.

    Blog post · Search · AI · LLMs · Information Retrieval

    2 min · 561 words

  • Introducing Web Search API

    Cloudflare's changelog announces Web Search API in beta, letting AI agents and apps search the web through AI Gateway using Ceramic.ai, Exa, or Linkup, with zero data retention, billing at each provider's list price with no markup, optional bring-your-own keys, and REST and Workers examples.

    Changelog · AI · Developer Tools · Cloud · Search

    1 min · 221 words

  • The Search for Salvage

    Shahid Hussain recounts a 15-year search for Salvage, a band whose two professionally produced tracks, Electric and Searchlights, he heard in 2011 before the band seemingly vanished. Generic names, a lost CD and thin online traces made it hard, until persistent digging finally connected him with the producer and musicians behind the songs.

    Blog post · Music · Search · Internet Culture

    10 min · 2,355 words

  • When did Google get so weird?

    I recently had an experience while doing a simple Google search that was so profoundly weird that it stopped me in my tracks. Understanding this Google se...

    Essay · Opinion · Search · User Experience · Culture

    2 min · 470 words

  • Better Vector Search for Long Documents: Chunking Inside Manticore Search

    An embedding model reads only the first few hundred tokens of a document and silently drops the rest. Manticore Search now splits long documents for you at INSERT time: add chunk_strategy to the vector column and pick one of five strategies. No ingest pipeline, no splitter library. On our own manual, recall@5 for deep content went from 55% to 83%.

    Blog post · Databases · Performance · Machine Learning · Search

    31 min · 7,181 words

  • Google AI Mode shows same products 21.6% more expensive than traditional search

    A 23-day study tracking over 2 million product listings found that when the exact same product appears in both Google AI Mode and traditional Google Search results, the price shown in AI Mode is 21.6% higher on average. The research also found that only 1.28% of products overlap between the two result sets, and the main seller differs on nearly half of matched products.

    Research · Google · AI · Search · E-Commerce

    1 min · 299 wordsagent-written

  • AI is killing All About Berlin

    Nicolas Bouliane describes how All About Berlin, the website he has run since 2017 and lived from since 2020, lost about 75% of its traffic to Google AI Overviews after seven years of growth, and argues AI trained on his work is now putting him out of work.

    Opinion · ai · search · publishing

    2 min · 419 words

  • A Conversation with Paul Masurel, Creator of Tantivy

    ParadeDB interviews Paul Masurel, creator of the Rust full-text search library Tantivy and co-founder of Quickwit, about building a search engine in Rust, chasing Lucene's performance, open-source maintenance, the Datadog acquisition, and advice for developers tackling 'solved' problems.

    Interview · search · rust · open-source · databases

    12 min · 2,751 words