How fast do LLMs pick up new information from the web?
How fast do LLMs pick up new information from the web? I ran a simple AI search experiment to find out.
The setup
- I invented several new English words that didn’t exist anywhere online.
- For each word, I wrote a definition-heavy page.
- I published them in different formats: a news article, a homepage, a product page and a blog post on existing sites; a public Notion doc; and brand-new sites with exact-match domains, like
zemuretomal.info. In total: 30 pages across 3 sets, each featuring a unique term. - Some sites included
llm.txt, some didn’t. - No backlinks, no social signals, no indexing requests.
Then I waited. Every day I searched for each term in ChatGPT, Gemini, Perplexity, DeepSeek, Google and Bing, both as plain queries and with the site: operator.
Five days later
- Gemini showed one definition on day one, before Google showed the page as indexed. Later it stopped showing it entirely, even though the page is now indexed. Possibly a content filter, or resource optimization suppressing low-signal terms.
- ChatGPT gave full definitions with source links, even when the pages weren’t visible on Google or Bing. It’s clearly using other indexing datasets.
- Perplexity performed surprisingly well. It consistently surfaced correct definitions and linked to the source pages quickly.
- DeepSeek was the last to catch on.
Which pages worked best
- News articles were picked up first by several models, possibly because of their semantic structure or assumed freshness.
- Exact-match domain pages also did well. Focused, on-topic and self-contained: LLMs seemed to like that.
- Homepages did better on visibility.
- Public Notion docs were invisible. I didn’t expect much, but I needed something to compare with.
Other findings
- Search engines lagged behind. Google indexed most pages by day five, Bing only one. LLMs started showing content before Google did.
llm.txtdoesn’t help.- Definition-style clarity matters. Pages with a single semantic purpose, explaining one concept, seem to get surfaced faster.
- Perplexity and ChatGPT showed the strongest “indexing” behavior, and they can clearly be influenced by what we put online.
This wasn’t about traffic. It was about visibility. Next, I want to test whether synthetic pages at a larger scale can influence real search topics.
Get the next one by email
A short email when there's something worth sending: experiments in search and AI, what I'm building, and what I learned the hard way.
Unsubscribe from any email. Read past issues.