GDELT Blog
blog.gdeltproject.org · Company blog · on HN since 2016
The blog of the GDELT Project, which maintains an open global news and events database, covering datasets, BigQuery queries and LLM experiments.
What HN saysHN commenters point to GDELT for its real-time global news map and for translating non-English news into searchable English, plus LLM failure-mode posts.
16HN people shared it
8linked it in comments
8stories submitted
12story points
10 months agolast shared
2016people per year2026
Most-shared posts
- 1GDELT 2.0: new release of open Global Event Database updated every 15 min4 people · 1 points · first shared 2017 · 1 comments on HN
- 2Google BigQuery and 3.5M Books: Sample Queries1 people · 3 points · first shared 2016 · discussion on HN
- 3Gemini 3.0 Deciphered the Mystery of a Nuremberg Chronicle Leaf's1 people · 3 points · first shared 2026 · discussion on HN
- 4Entity Extraction: LLMs versus Classical Neural Model1 people · 1 points · first shared 2023 · discussion on HN
- 5NGram Datasets to Explore Television News' Coverage of Trump and Mueller1 people · 1 points · first shared 2019 · discussion on HN
- 6Generative AI Experiments: LLM Secret Guardrails (2023)1 people · 1 points · first shared 2024 · discussion on HN
- 7The Strange Case of a Rise in HTTP 451 Errors and GDPR1 people · 1 points · first shared 2021 · discussion on HN
- 8March 2022: Belarusian, Russian and Ukrainian Broadcasts Translated into English1 people · 1 points · first shared 2023 · discussion on HN
- 9An interactive realtime map of the worlds news1 people · first shared 2024
- 10Llm infinite loops failure modes the current state of llm entity extraction1 people · first shared 2024
- 11Gdelt translingual translating the planet1 people · first shared 2020
- 12Peering into the visual landscape of half a billion news images with googles cloud inference api1 people · first shared 2018
- 13
What HN people wrote when they linked it
namibj · 2018-03-18
Regarding graph databases: does anyone have specific recommendations regarding something suitable to hold 2-digit TB of graph data, and allow many queries regarding how datapoints that come up are connected to some areas of interest, through the big knowledge graph[0]?
I'm looking into doing some prediction work based on it, and have not found any suitable data store so far, which would work well with it, due to the size and budged restraints limiting storage to NVMe modules, instead of DRAM.
Any help finding a suitable datastore would be greatly appreciated.
[0]: http://data.gdeltproject.org/documentation/GDELT-Global_Knowledge_Grap… https://blog.gdeltproject.org/gdelt-2-0-our-global-world-in-realtime/
yencabulator · 2024-02-09
Well the ending sure sounds like an LLM getting stuck:
> "the little computer knew then that computers would always grow wiser and more powerful until someday—someday—someday—…"
https://blog.gdeltproject.org/llm-infinite-loops-failure-modes-the-cur…
moandcompany · 2024-01-23
Somewhat Related - You may like the GDELT Project: https://www.gdeltproject.org/
https://blog.gdeltproject.org/an-interactive-realtime-map-of-the-world…
chris_f · 2020-10-21
The one nice thing about GDELT is it translates non-english language news so that you can use an english search term and see articles in different language. It's not perfect (i.e. machine translation), but I am not aware of any other service that provides similar functionality.
More info: https://blog.gdeltproject.org/gdelt-translingual-translating-the-plane…
(unrelated: scrolling on that page is horrible)
wombatmobile · 2020-10-21
Thanks for compiling that list. I have had a quick look and downloaded it for a longer look.
Some GDELT methodology is extolled here:
https://blog.gdeltproject.org/gdelt-2-0-our-global-world-in-realtime/
_____smurf_____ · 2020-04-20
How is this different from GDELT https://blog.gdeltproject.org/gdelt-2-0-our-global-world-in-realtime/
rasmi · 2018-09-20
Here's a neat use case analyzing GDELT data:
https://blog.gdeltproject.org/peering-into-the-visual-landscape-of-hal…
dholowiski · 2016-02-16
Nope, there was almost no mention of what this was actually used for. The closest I found was a mention of the final output:
"single output files, tab-delimited with data available for each year, merging in publication metadata and other information about each book"
[edit] More info in a link at the bottom of the article: http://blog.gdeltproject.org/3-5-million-books-1800-2015-gdelt-process…