# Thinking Machines on Real-Time AI Interaction Models

- Original post: https://www.twitter.com/i/status/2118699950947099107
- Source account: [@rosenacry](https://x.com/rosenacry)
- Source language: English
- Duration: 2:08
- Published: 2026-11-07
- Canonical URL: https://www.translate.mom/transcript/BJbQA6SM8ytX/en/thinking-machines-on-real-time-ai-interaction-models

## Transcript

[0:00](https://www.translate.mom/transcript/BJbQA6SM8ytX/en/thinking-machines-on-real-time-ai-interaction-models) The reason why we even started Thinking Machines is because we wanted to build a frontier AI lab that's really focused on, um, really human AI collaboration piece, and that means a lot of things, and there are specific research bets that go into that.

[0:18](https://www.translate.mom/transcript/BJbQA6SM8ytX/en/thinking-machines-on-real-time-ai-interaction-models?t=18) But we wanted to showcase, um, our work in one of the first bets through the interaction models.

[0:26](https://www.translate.mom/transcript/BJbQA6SM8ytX/en/thinking-machines-on-real-time-ai-interaction-models?t=26) And the interaction models are a new kind of model.

[0:29](https://www.translate.mom/transcript/BJbQA6SM8ytX/en/thinking-machines-on-real-time-ai-interaction-models?t=29) If you consider the types of models that we work with today, they're very, um, turn-based. Mm.

[0:36](https://www.translate.mom/transcript/BJbQA6SM8ytX/en/thinking-machines-on-real-time-ai-interaction-models?t=36) And so you talk, they talk, then they go off and think.

[0:40](https://www.translate.mom/transcript/BJbQA6SM8ytX/en/thinking-machines-on-real-time-ai-interaction-models?t=40) Um, once you've given sort of a prompt on what it is that you want to do, and while they're thinking, it's almost like they're deaf and blind. Mm.

[0:49](https://www.translate.mom/transcript/BJbQA6SM8ytX/en/thinking-machines-on-real-time-ai-interaction-models?t=49) They cannot perceive anything else about what's going on, and then it's your turn, and while you're talking, um, they really cannot perceive anything about how you're talking.

[1:01](https://www.translate.mom/transcript/BJbQA6SM8ytX/en/thinking-machines-on-real-time-ai-interaction-models?t=61) It's not happening in real time. And by contrast, our interactions with each other are very rich.

[1:08](https://www.translate.mom/transcript/BJbQA6SM8ytX/en/thinking-machines-on-real-time-ai-interaction-models?t=68) There is a lot of information in our interactions when we are silent, when we're thinking, when we're interrupting one another.

[1:18](https://www.translate.mom/transcript/BJbQA6SM8ytX/en/thinking-machines-on-real-time-ai-interaction-models?t=78) And so interaction models are able to capture all of these neurons.

[1:23](https://www.translate.mom/transcript/BJbQA6SM8ytX/en/thinking-machines-on-real-time-ai-interaction-models?t=83) They're not turn-based. They're more like time-based- Oh ... interaction, where they're continuously taking in audio, text, video, and continuously providing output.

[1:34](https://www.translate.mom/transcript/BJbQA6SM8ytX/en/thinking-machines-on-real-time-ai-interaction-models?t=94) Now, we cut this up in chunks of twenty milliseconds, and this enables you to actually, uh, catch these things like interruptions and simultaneous speech, um, and really create a rich, high bandwidth interaction between humans and machines- Mm ... which we think is critical to actually enable,

[1:56](https://www.translate.mom/transcript/BJbQA6SM8ytX/en/thinking-machines-on-real-time-ai-interaction-models?t=116) um, agency and, uh, and, and enable people to be more in this loop- Mm-hmm ... um, as we advance AI further and further.