Can AI hold identity, follow protocol, show empathy, and do it all under 500ms?
We evaluated this across 50 healthcare coaching episodes, five tracks, and two models. Initial results from a constrained production domain.
Making one of the first voice agents that feel human.
Not "human-like." Not "empathetic-sounding." Actually indistinguishable from a trained professional, at the speed of natural conversation.
Persona 001 runs healthcare coaching calls in production. 25-minute intakes, weekly check-ins, PHQ-2 screenings. Real patients scripts, real clinical constraints.
Here is how 🧵
Remember that you are not talking to "the AI", but you are using a powerful text generator to co-create a story about the interaction between a user and the simulacrum of an Artificial Intelligence.
If you want to research interventions to gradual disempowerment or the intelligence curse, @LRudL_ and I are mentoring a @MATSprogram stream this autumn.
Many people have asked me “what’s the plan to make this go well?” Right now, there’s not one. You should help fix that.
🧵
i still think we're in an automation-augmentation race: whether the future features fulfilling human work isn't something we discover, but depends on technical and policy work today.
if you're looking to join the race on the side of augmentation, this is a great place to start.
(Researcher 1): Astonishing. The baby human crawls towards the Claude mother, despite the GPT mother scoring higher on benchmarks.
(Researcher 2): It’s just creature comforts, isn’t it? The baby human craves warmth and tenderness, even at the cost of frontier math performance.
we do need to become a hybrid society as the amount of info and noise increases but with the current state of ai it’s no wonder people are hesitant. its kinda like a feudal system of full trust in the longterm sensibility.
maybe if wr could build trust / rapport with ai and trust them to deal w shit we would go into this future faster (ai adapting to our collaboration way instead of the other way)