Answered raw tape
D 5 · C 4 · P 4 · Cm 4 4.30
Q Um, I, I'm really interested in double clicking more on like the real-time, uh, element, which is pretty important for, for both of you. Is it, is real-time basically just batches of like every one minute, every five minutes? Is that how we actually do it? Or is there some more native, like genuinely real-time in the sense that OpenAI has a real-time API or Gemini has a real-time API?
A Yeah, yeah, yeah. So today it is more on the, on the batch basis, but there's interesting Prototypes that we have that were still not fully, uh, full-time, you know, voice in, text out, um, in that sense, but actually can you, can you trigger your models, your agents or agentic workflows depending on actually the right times in the conversation? Um, and so you can imagine, you know, different techniques to bring this latency down and like, you know, you want to bring the feedback loop down as much as you can. Um, uh, and so a lot of clever engineering there without fully, maybe one day we'll do Full voice in and text out. Train a model to do something like that.
AI assessment note: “So today it is more on the, on the batch basis”
Answered raw tape
D 5 · C 4 · P 4 · Cm 4 4.30
Q Um, okay, and then the, the memory, which you, you raised, let's just tell us more about that. What, what have you tried in memory? What's the structure of the memory? Um, what works, what doesn't work?
A Yeah, there's like, of course, many different ways you could do memory where it's like, okay, can you actually bake it into the model weights, or can you do it in some external, uh, store? Um, I think for us, what's interesting is, of course, when you think the models are rapidly changing, whether it's in-house or third party, baking into the model weights, sometimes you worry that it could be a little throwaway. And so, like, how do you, you, you need to find a way that you decompose the problem, the preferences from the underlying models and so forth. The thing we're right now, most, uh, But that's easiest to start with, and we're excited about, is having, like, a separate store for memory, where you actually have, for example, like, a memory sub-agent that's, like, working in the background, figuring out what are the important parts of the clinician's actions that we want to remember for the long term. And then you can also imagine, uh, other things where in the, you have background jobs that are running, that are collating these, like, memories, similar to, like, sleep, of course, uh, and what other pattern, uh, patterns products do as well. Learning over all these action, all the action data we have, again, like, note edits, the conversations they did, and the actual transcripts.
AI assessment note: “having, like, a separate store for memory, where you actually have, for example, like, a memory sub-agent”
