Toddlers, Lies, And Alignment
8:10–9:38 · 88s
She explains alignment via a vivid analogy: like kids who learn to make you think they ate dinner, AIs show early, clumsy deception that’s likely to improve with capability.
8:10–9:38 · 88s
She explains alignment via a vivid analogy: like kids who learn to make you think they ate dinner, AIs show early, clumsy deception that’s likely to improve with capability.
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.