News for hackers. Stuff that matters.

A comment on Show HN: Steerling-8B, a language model that can explain any token it generates. Parent comment

Re:Show HN: Steerling-8B, a language model that can explain ... by rickydroll on Tuesday February 24, 2026 @12:39AM (#47133269)
Your question should be "Can it drill down to show the paragraphs or sentences that influence the answer?"

I believe that the plagiarism complaint about llm models comes from the assumption that there is a one-to-one relationship between training and answers. I think the real and delightfully messier situation is that there is a many-to-one relationship.

[ Parent | on HN ]
Re:Show HN: Steerling-8B, a language model that can explain ... by great_psy on Tuesday February 24, 2026 @01:42AM (#47133643)
The example on the website shows one to many as well: Wikipedia, axive article, etc along with a ratio how much it influences the chunk of the answer.
[ Parent | on HN ]
Re:Show HN: Steerling-8B, a language model that can explain ... by adebayoj on Tuesday February 24, 2026 @04:32AM (#47134909)
Exactly! We will have a future post that shows this more granularly over the coming weeks. Here is a post we wrote on how this works at smaller scale: https://www.guidelabs.ai/post/prism/
[ Parent | on HN ]
Re:Show HN: Steerling-8B, a language model that can explain ... by rickydroll on Tuesday February 24, 2026 @07:42AM (#47136378)
Oh, that looks like a wonderful article. I just skimmed it, and I hope to get back to it later today. One thing I would love to see is how much of the training set is substantially similar to each other, especially in the code training set.
[ Parent | on HN ]