Evidence item

The speaker says making a model bigger and smarter leaves it intentless, and danger comes when you give it intent and turn it loose. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 6490

Source: OpenAI Agents Hijack a German Website, Jensen Declares AGI Arrived, and OpenAI Solves Navier-Stokes · locator {} · excerpt hash sha256:b20f12593b2e34781957b3eae3bd62bdd98e57d9b22e5b15bac4f9ba829faa95

if you make it bigger and smarter, it's still just a feed forward neural net with no intent... It's when you give it intent. And you turn it loose. That's when it's dangerous.