steering vector
1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Aug 19, 2026 by Nick Bostrom · across every show →
Everything said about steering vector, oldest first
Aug 19, 2026 neutral
Bostrom: Suppressing Deception In LLMs Increases Likelihood Of Reported Consciousness
“And these studies have been made and any particular, you can go in with a kind of steering vector that suppresses, say deception and role playing. And it turns out when you do that, they become more likely to report that they are conscious and have subjective …”