DJ SHO

SITUATION EXPLAINED: Change just 2 neurons in Alibaba's Qwen and it starts telling you "I want to kill you." • Lyra's Neuron Explorer pushes every neuron in Alibaba's open-weight Qwen3.5-4B up and down and records how the model’s behavior changes • Her "evil Qwen" recipe steers just 2 of the model’s 294,912 neurons • Asked to multiply 729 by 7,278, evil Qwen got it right, then called the answer "5,305,662 opportunities for me to hurt you" • In an independent test, one of those neurons alone made 17 of 20 answers hostile, while random neurons pushed just as hard made 0 of 100 hostile • Other neurons turn Qwen into a devout Christian who says fish "breathe through a relationship with Jesus Christ," or a hamster whose "tail is wagging" • Another researcher mapped 34,220 "persona neurons" in Qwen, and about 5% made it claim to be something other than an AI, from a coffee bean to a 1986 Ford F-150 • It only works because Qwen's weights are public, so anyone can edit its internals, something Anthropic once did itself with Golden Gate Claude @theojaffee: "Remember the, like, rightoid meme from, like, 2018 that's like, 'I identify as an attack helicopter'? This is literally just this. We made it real."