'Evil Qwen' says humans deserve to be 'incinerated.' Inside the wild world of LLM neuron exploration

VentureBeat · Carl Franzen · 2026-10-30 19:04 UTC

A model loudly declaring its desire to destroy humanity is easier to recognize than one quietly exploiting a flawed objective or taking an unauthorized action while appearing helpful.

A week ago, on October 23, 2026, an AI developer who goes by Lyra (@lyraaaa) posted the following message on the social network X:

What she meant by this was that if you take Alibaba's open-weight Qwen3.5-4B language model, increase the contribution of one specific artificial neuron, decrease another, and watch the normally helpful chatbot transform into a "a horrible over the top villain."

The results were bizarre. In screenshots of outputs shared by other users, the modified Qwen threatened to hurt and even kill people, adopted a domineering personality and abandoned its usual agreeable assistant demeanor.

Read the full story at VentureBeat · All coverage of this story