Googling a sentence yields copycat sites and poor results in general
Take the following sentence for example, searched in google with quotation marks included: "Booster seats, car seats and seat belts are equally effective at saving the lives of children" This is a sentence that originated (as far as I know) from here: http://www.montana.edu/news/17359/msu-studies-investigate-ef.... The first page of results contains various websites that, on the surface, contain the quoted sentence but on closer inspection, contains the entire original content from montana.edu verbatim. Additionally, the first 5 results are from sciencedaily.com,…
Googling a sentence yields copycat sites and poor results in general launched on July 27, 2018 with 16 votes, #832 of 2,673 launches that month and more than 75% of that year's launches.
In plain words
This is a discussion highlighting issues with Google search results when using exact phrase queries. The problem identified is that search results often return numerous copycat websites that have republished original content verbatim from academic sources, rather than surfacing the original source. The example demonstrates how a specific sentence from a Montana State University research article produces mostly results from sites like ScienceDaily, which appear to contain the phrase but are largely duplicative content. The concern raises questions about search engine ranking algorithms and content discovery prioritization.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Take the following sentence for example, searched in google with quotation marks included: "Booster seats, car seats and seat belts are equally effective at saving the lives of children" This is a sentence that originated (as far as I know) from here…
Does a similar job
all alternatives →- IMI made a website to semantically search ArXiv papers2024 · papermatch.mitanshu.tech · ▲324
As a grad student (and an ADHDer), I had trouble doing literature review systematically. To combat this, I made a website that finds similar papers using the meaning of the thing I am looking for. I used MixedBread's [^1] embedding model to generate vectors from the abstracts. I store and search similar vectors using Milvus [^2] and finally use Gradio [^3] to serve the frontend. I update the vector database weekly by pulling the metadata dataset from Kaggle [^4]. To speed up the search process on my free oracle instance, I binarise the embeddings and use Hamming distance as a metric. I would…
Tabstack Web ResearchJun 2026 · tabstack.ai · ▲168Run a research agent with cited answers in a single API call
- WSWeb search using a ChatGPT-like model that can cite its sources2022 · beta.sayhello.so · ▲318
We’ve trained a generative AI model to browse the web and answer questions/retrieve code snippets directly. Unlike ChatGPT, it has access to primary sources and is able to cite them when you hover over an answer (click on the text to go to the source being cited). We also show regular Bing results side-by-side with our AI answer. The model is an 11-billion parameter T5-derivative that has been fine-tuned on feedback given on hundreds of thousands of searches done (anonymously) on our platform. Giving the model web access lessens its burden to need to store a snapshot of human knowledge…
More growth this month
the category →
wallhop is a free paywall bypass. Paste any article link to read it without paywall popups, ads or clutter. No signup, no extension. A simple 12ft.io alternative.
Growth · 13d ago · wallhop.io
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, July 2018
the whole month →
A fully interactive, realtime and modern browser rendered to TTY
Life & fun · 2018 · brow.sh
Record terminal sessions as SVG animations. Contribute to nbedos/termtosvg development by creating an account on GitHub.
Dev tools · 2018 · github.com
