Our Smallest, Most Efficient Model: Muse Ember

Re:Our Smallest, Most Efficient Model: Muse Ember by drillsteps5 on Monday November 09, 2026 @04:57PM (#50432839)

Exactly what I was thinking. If this model will be used for coding, does it need to be fed the entire (mostly pirated) collection of works from Anna's Archive? Probably not. Maybe some, primarily computer-science oriented.

The main corpus would be a collection of thoroughly reviewed, clean, logical, well-documented, and secure code in whatever languages this thing will need to be an expert in.

This way we could also look into reasonable compensation agreement with authors of the code and the books/articles, if and when applicable.

Has no one tried that?

[ Parent | on HN ]

Re:Our Smallest, Most Efficient Model: Muse Ember by ElectricalUnion on Monday November 09, 2026 @06:42PM (#50433998)

Unless your task happens to be completely contained in the set of your "curated works", that is, trivial and computer-sciency, the resulting model is likely to have for example absolutely no concept of common sense, society, the natural world, what humans consider artistic or of good taste. It will probrably make, say, a good and correct compiler, but fail spetacularly on anything else more complex that a toy crud.

[ Parent | on HN ]

Re:Our Smallest, Most Efficient Model: Muse Ember by drillsteps5 on Tuesday November 10, 2026 @12:40AM (#50436507)

Are you saying that LLMs have common sense, good taste, or can determine what is artistic?

[ Parent | on HN ]