News for hackers. Stuff that matters.

A comment on Our Smallest, Most Efficient Model: Muse Ember. Parent comment

Re:Our Smallest, Most Efficient Model: Muse Ember by ezst on Monday November 09, 2026 @02:38PM (#50430710)
Wouldn't that be a sign that those models were trained to optimise that test case specifically, as in, by exhibiting equal or higher performance while using less power?
[ Parent | on HN ]
Re:Our Smallest, Most Efficient Model: Muse Ember by ourcat on Monday November 09, 2026 @04:43PM (#50432672)
Indeed. And that they were all trained to give it a red scarf, which was not asked for.
[ Parent | on HN ]
Re:Our Smallest, Most Efficient Model: Muse Ember by 9dev on Monday November 09, 2026 @05:57PM (#50433519)
At this point, even if the labs wouldn’t actively pelican-max their models, isn’t the training corpus full of pelicans already? Funny to think how one models choice of adding a red scarf in one of Simon’s earlier experiments might have led to an archetype of pelicans riding bicycles…
[ Parent | on HN ]
Re:Our Smallest, Most Efficient Model: Muse Ember by flir on Tuesday November 10, 2026 @08:08AM (#50439790)
Not just pelicans, but pelicans with commentary about how good they are. simonw is accidentally running the world's least efficient hill climbing algorithm.
[ Parent | on HN ]
Re:Our Smallest, Most Efficient Model: Muse Ember by bagacrap on Tuesday November 10, 2026 @09:51AM (#50441201)
They all have a red scarf and a fish in a front basket
[ Parent | on HN ]