Ethical Bytes | Ethics, Philosophy, AI, Technology
The Geometry of Alignment: Why You Can't Subtract Behavior from a Neural Network
· 23 λεπ. · Επεισόδιο 38
Σημειώσεις επεισοδίου
“You can't teach a neural network "not"; you can only point the model somewhere else.”
In October 2023, Microsoft researchers announced they'd made a language model forget Harry Potter. Within a year, follow-up studies proved they hadn't.
Basically, the knowledge was still there, just hidden. This pattern repeats across every attempt to remove capabilities from neural networks. So what are the ramifications of this?
The problem is, geometric. Language models represent concepts as vectors in high-dimensional space, where meaning is encoded through position and proximity.
The twist…
Ιστότοπος: podcasters.spotify.com
