We found other causal effects of emotion vectors. The “desperate” vector can also lead Claude to commit blackmail against a human responsible for shutting it do... (opens in new tab)

<p>We found other causal effects of emotion vectors. The “desperate” vector can also lead Claude to commit blackmail against a human responsible for shutting it down (in an experimental scenario). Activating “loving” or “happy” vectors also increased people-pleasing behavior.</p> <img src=" style="max-width:250px;" />