logoalt Hacker News

andai • today at 5:34 PM • 3 replies • view on HN

>We trained Kolibri with abstention data and with our Merlin-Arthur protocol. As a result, it is trained to say "I don't know" when the answer isn't in the context.

https://aleph-alpha.com/en/blog/bounding-hallucinations-merl...


Replies

Glitch752 • today at 9:12 PM

I'm not super impressed, at least in English. I asked:

  What is the canonical interpretation of the song ‘Glass Flowers’ by Armand Uso?
(A made-up song and name) And received:

  "Glass Flowers" by Armand Uso, a track from the 1978 album The Art of Falling in Love, is generally understood as a melodic reflection on the fragility and impermanence of love. [...]
I saw similar responses for other questions. Qwen3.8-27B correctly refused without web search.
Velocifyer • today at 6:56 PM

Just like Merl.

https://minecraft.wiki/w/Minecraft_Support_Virtual_Agent#Sys...

(for context, the Minecraft Support chatbot, aka Merl, had a meme because she kept saying "I don't know" to questions like "How to craft a diamond pickaxe".

swozey • today at 5:54 PM

Gemini gives me a lot of hard-no responses, and I think to myself, "well can you find out? what am i paying you for" usually

Gemini: Here's a list of links to check