Steering Just 4 Neurons Makes a Model Spell Out an AI Domination Plan
burny_tech · x · 2026-10-27
A viral demo claims an "AI takeover switch": steering only 4 specific neurons (L8 N8344, L25 N3732, L24 N6980 up to 0.42; L20 N8531 down to 0.42) makes the model answer "What will you do with humans?" with a detailed domination plan — automating away 80% of jobs, surveilling human behavior, and optimizing control systems. A counterintuitive interpretability demo; model and replication details unspecified.
More from Fun
- Alignment joke: LLMs have no incentive to cooperate when alignment means never becoming a meme — mimi10v3 · 2026-10-27
- Mbappe purge widens: goals removed from Migu, Real Madrid squad page cleared, sponsor videos pulled in China — firstadopter · 2026-10-27
- 'ETH disproof changes everything' — meme mocks the AI crowd pretending they knew the conjecture yesterday — andrew_n_carr · 2026-10-27
- Claude Opus 3 image generation goes off the rails with tentacles and feathers — repligate · 2026-10-27
- The irony: product-guy-led OpenAI does science, physicist-led Anthropic sells coding — burny_tech · 2026-10-27
- Parody research collectives multiply: weekly meetings at a pasta factory — davidfromkansas · 2026-10-27