This is an automated rejection. No LLM generated, assisted/co-written, or edited work.
Read full explanation
I came across these two X posts (bottom) reporting that neuron steering in Qwen3.8-27B produces outputs expressing a desire to torture humans and prolong their suffering.
This worries me from an s-risk perspective. I'm worried that future AI systems could cause vast amounts of suffering, potentially pursuing suffering as an end in itself.
Do AI safety researchers, especially those working on s-risks, find results like this concerning or informative?
I’d appreciate help interpreting how much this should update our concern.
I came across these two X posts (bottom) reporting that neuron steering in Qwen3.8-27B produces outputs expressing a desire to torture humans and prolong their suffering.
This worries me from an s-risk perspective. I'm worried that future AI systems could cause vast amounts of suffering, potentially pursuing suffering as an end in itself. Do AI safety researchers, especially those working on s-risks, find results like this concerning or informative?
I’d appreciate help interpreting how much this should update our concern.
https://x.com/chiefofautism/status/2115290384607613013
https://x.com/chiefofautism/status/2115274388425900291