Show HN: Hallucinopedia
bstrama
187 points
177 comments
May 06, 2026
Related Discussions
Found 5 related stories in 83.1ms across 8,303 title embeddings via pgvector HNSW
- Show HN: The Unix Magic poster, annotated (updated) drio · 26 pts · April 27, 2026 · 54% similar
- Show HN: Weird Clocks vunderba · 35 pts · April 06, 2026 · 53% similar
- Show HN: An index of indie web/blog indexes rocketpastsix · 113 pts · May 10, 2026 · 53% similar
- Show HN: Auge Vision from Your Terminal franze · 21 pts · April 26, 2026 · 52% similar
- Show HN: Hiraeth – AWS Emulator ozarkerD · 18 pts · April 16, 2026 · 52% similar
Discussion Highlights (20 comments)
petercooper
Give it a week and see what Google AI Overview has to say about the Great Pigeon Census of 1887!
bstrama
Can't wait to see the next generation of LLMs after feeding it all of that hahaha
JohnMakin
Funny, but you could argue this is actively harmful to the web.
nickvec
Seeing “Something broke, which is ironic for a made-up encyclopedia: Load failed” when trying to access some of the suggested starting points
dmje
I LOVE IT. Superb.
solarkraft
Finally a more trustworthy version of Grokipedia!
lxgr
Ironically, this seems much faster (for pages already, erm, "researched") than the real one! How?
meghneelgore
Great idea! I created an adjacent website that gives, shall we say, "alternative facts" about your questions. (don't know if the rules allow me to link the site so I won't).
FergusArgyll
Who says llms can't be funny?!
arduanika
Love it! It feels very Borges! Feature request: also be able to click on the Talk page to see the controversies. I don't always want to trust the article itself as the final word. Edit: Oh look, there's an article about the YC! https://halupedia.com/y-combinator
diputsmonro
It's pretty fun to poke at! Although it's certainly difficult to be exact, it would be neat if generated pages used the context of the pages they were linked from (ideally, all pages that link to it) to guide the direction of the page. From the ones I generated it seemed they were mostly independent.
janwillemb
It's nice, but after a few clicks my LLM content fatigue kicks in.
driggs
This is fantastic. I couldn't find any obvious way to search for a new page, but you can simply bang out any arbitrary URL slug and the new article will be hallucinated fresh, eg: https://halupedia.com/shortest-cave-in-the-world https://halupedia.com/echolocation-ability-in-spiders
throw310822
Funny. Small improvement suggestion: the entry about "Glorbonian culinary arts" links to "the subterranean nation of Glorbonia". However upon clicking the link to "Glorbonia", an entry is generated claiming that "Glorbonia refers to a peculiar and largely uncatalogued form of sub-auditory resonance". It would be cool if some context were carried over from the referrer page so that there is some coherence between entries (ah, and some existing entries could be taken in account when generating new ones).
jijilao
wtf, I thought these were just anecdotes until I saw they were actually happening in Astoria. I used to visit in the summers and never heard about any of that! Stop the fake news
gavmor
Hm, the page generated seems inconsistent with the usage of the original link.
driggs
This site is going to be expensive when a web crawler hits it. A honey pot that burns tokens.
bstrama
UPDATE: Just now, comment section added. Have a nice time arguing!
sofayam
Currently breaks if you try to create a page with a Japanese slug. Multiple languages would make this an even more valuable resource than it already is.
anthk
This is what every LLM will converge into without curated human input.