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 researcher tell me how worried we should be about this phenomenon?
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 researcher tell me how worried we should be about this phenomenon?