News for hackers. Stuff that matters.
Re:Star neuroscientist may have manipulated data to support ... by nerdponx on Friday December 01, 2023 @01:22PM (#38490265)
You're entitled to your own opinion of course, but your conclusions appear to be based on beginner-level misunderstandings. That doesn't seem like a constructive or productive way to conduct oneself through life.
Re:Star neuroscientist may have manipulated data to support ... by h2odragon on Friday December 01, 2023 @04:13PM (#38492482)
you should see my rants about why normalizing weights is a bad idea and how a limited context window is effectively random interpolation