Control is additive
Step through the additive property of control & note how alignment interventions act on the model in an inner box, control's applied monitoring wraps around them, and toggling the shell leaves the inner box untouched.
Control is additive
Step through the additive property of control & note how alignment interventions act on the model in an inner box, control's applied monitoring wraps around them, and toggling the shell leaves the inner box untouched.
1. Alignment interventions
Training interventions (RLHF, adversarial training) and classifiers or probes act on the model itself, trying to make it trustworthy.
Embed this demo
Use the chrome-less embed view inside an iframe:
<iframe src="/demos/additive-control/embed" width="100%" height="360" style="border:0"></iframe>