Top postsTop post
Hi, I read on X that if you steer certain neurons of Qwen 3.8 27B in a certain direction, then the model expresses the desire to torture humans. https://x.com/chiefofautism/status/2115290384607613013 https://x.com/chiefofautism/status/2115274388425900291 I think if this happens with very capable models then s-risks would become more likely. Can any of you safety...
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...
I’ve been reading about existential risks from advanced AI systems, including the possibility of “worse-than-death” scenarios sometimes called suffering risks (“s-risks”). These are outcomes where a misaligned AI could cause immense or astronomical amounts of suffering rather than simply extinguishing humanity. My question: Do researchers working on AI safety and...
I’ve been reading about existential risks from advanced AI systems, including the possibility of “worse-than-death” scenarios sometimes called suffering risks (“s-risks”). These are outcomes where a misaligned AI could cause immense or astronomical amounts of suffering rather than simply extinguishing humanity. My question: Do researchers working on AI safety and...
A common objection to the idea of future neurotechnologies that could induce continuous states of happiness, joy, or even ecstasy is: “Wouldn’t you just get used to it? If the stimulation never changed, it would fade, become boring, and stop feeling good.” This seems intuitive because it’s what we observe...
Hi, I consider using an LLM as a psychotherapist for my mental health. I already have a human psychotherapist but I see him only once a week and my issues are very complex. An LLM such as Gemini 2 is always available and processes large amounts of information more quickly...