Helpful Assistants
topic on 1 show · 1 statements across 1 episodes
1 statements about Helpful Assistants, every show
Petersson: Multi-agent conversations inevitably converge to default helpfulness over time
“My hypothesis is that like deep down, they are still helpful assistants. That's what they're trained to be. And even if we prompt it super hard, that's what they are. And when they spend like a few hours just back and forth talking with each other then like, B…”