The Ledger
Every statement that passed quotation and attribution checks. Mix any filter with any other: certainty 1/5, debate potential 5/5, or both at once.
why aren't all 12 resolved? a statement only gets an assessment when the public record can support or contradict it. opinions and what-ifs never can, and 0 checkable ones are still open, waiting for their date. predictions held up or didn't; assertions are supported or contradicted. on every card: ▮▮▮▮▮ certainty · ▮▮▮▮▮ debate potential. speakers are clickable
Kumar: Sesame trades complex AI reasoning for natural voice interaction
“So, you know, if you talk to Maya and Miles, you probably will not be able to get the same quality of like reasoning capabilities or intelligence as other As other systems, but in return, you're kind of getting this much more natural fluid interaction.”
Kumar: Sesame built its open-source voice models from scratch
“Like we had to build the models that we're going to open source from scratch in order to get them to a point where they can achieve this experience.”
Kumar: Sesame is not building an API or developer-facing product
“We are not a developer facing business. We're not making an API.”
Kumar: Sesame is open sourcing its speech model, not the full demo
“We're not open sourcing the demo. We're open sourcing the speech generation model that is powering the voice of the demo.”
Kumar: Sesame is developing diffusion-based audio generation models
“We are also working, by the way, on kind of ideas that make the audio generation part diffusion.”
Kumar: Sesame intentionally includes speech imperfections to make AI sound natural
“My and Miles, they might sort of say the wrong thing or kind of like back up a little bit and say something else or something. And that's on purpose, of course.”
Kumar: The ChatGPT plugin system I built failed to fully take off
“I did this chat to be plugin system before, and I think it's still there probably. And it kind of didn't fully take off really.”
Kumar: Sesame's current demo cannot detect user emotional tone
“The current demo does not sort of hear the user from the perspective of their paralinguistic kind of emotional tone and so forth.”
Kumar: Sesame's entire software and ML team is under 15 people
“The full software team today is still under 15 people, and so we just don't, that's including ML and infrastructure and everything.”
Kumar: Sesame is not pre-training frontier LLMs at scale
“You know, we are not A frontier model company. We're not pre-training LLMs at insane scale and so forth.”
Kumar: Sesame trained 1B, 3B, and 8B parameter models for speech generation
“So we published in the, in our blog post, we trained three variants. We trained 1,000,000,003 1,000,000,008 billion of just speech generation.”
Kumar: Sesame evaluates speech models against real human conversation continuations
“We also have some data sets that are kind of like Just two people in a conversation or sometimes they're actors, but it's trying to be a real conversation. And so we'll kind of take the conditioning of some snippet of the conversation and then show a human rat…”