Anthropic has some similar findings, and they propose an architectural change (activation capping) that apparently helps keep the Assistant character away from dark traits (sometimes). But it hasn’t been implemented in any models, I assume because of the cost of scaling it up.
Anthropic has some similar findings, and they propose an architectural change (activation capping) that apparently helps keep the Assistant character away from dark traits (sometimes). But it hasn’t been implemented in any models, I assume because of the cost of scaling it up.