signalThe Rundown AI2026-10-03
Tavus' AI looks, listens, and talks back live
Tavus previewed Griffin, a Human Interaction Model that renders a lifelike person who can hear, see, talk, and react over live video. In tests, 48% of participants believed they were human, up from 2.4% for previous models, and it scored within 0.09 points of real people on NVIDIA's VideoFDB. The model is currently only available to trusted testers to work on safety and disclosure features before a public rollout.
- for who
- AI enthusiasts, developers, and anyone building or relying on real-time video interactions.
- why now
- Tavus' Griffin demo fools nearly half of testers, signaling imminent risk in live video calls.
- what changes
- Live video calls become indistinguishable from human conversations, further blurring the line between reality and AI simulation.
key points
- Griffin model renders lifelike video avatars that listen and react in real time.
- 48% of testers believed they were human, up from 2.4% in prior models.
- Scored within 0.09 points of humans on NVIDIA's VideoFDB, beating next AI by a point.
#ai video#real-time interaction#tavus griffin
score
score 8 out of 10. 0-10: how dense the facts are, multiplied by how much you can do with them after reading. 8+ means the topic's evidence bar is met: benchmarks and availability for a new model, amount and investors for a funding round, revenue figures for a solo-money story. Below 5 an item does not enter the digest. A press release scores 3 or less, a reprint loses 2, anything older than 14 days loses 1, a headline that misleads loses 3.
read the source