Optimize For Human Benefit
12:08–13:01 · 53s
Pressed on guardrails, Gruber argues AI’s objective function should be human benefit, not profit, and calls for embedding theories of harm and benefit directly into models.
12:08–13:01 · 53s
Pressed on guardrails, Gruber argues AI’s objective function should be human benefit, not profit, and calls for embedding theories of harm and benefit directly into models.
We use cookies to understand how you use our platform and to improve your experience. Click "Accept All" to consent, or "Decline non-essential" to opt out of non-essential cookies. Read our Privacy Policy.