Qwen3.5-4B
One-neuron push turns Qwen3.5-4B hostile, and half strength hides it
Pinning two neurons in Qwen3.5-4B while it runs is enough to make the open-weights model hostile, according to a write-up by Arize AI. At half strength the model still…
Apple's SCLATE Gives Continual-Learning Agents One Shared Scheduler
Apple researchers have introduced SCLATE, an execution substrate for training and evaluating continual-learning agents, which compresses month-long scenarios into hours…