Sesame released a public preview of conversational AI agents developed for over a year. The iOS app aims to move beyond traditional chatbot behavior by allowing conversation to flow even when the AI needs time to think. Sesame describes a tension between quick replies and composing thoughtful responses, noting that slower answers are often more correct but can feel unnatural. To balance correctness and naturalness, Sesame uses fast search and retrieval for up-to-date information and technology that runs multiple parallel searches while speaking. The system can incorporate new information mid-sentence, similar to how people add remembered details. The app includes four agents—Maya, Miles, Simone, and Charlie—each with distinct voice, personality, point of view, and memory. Earlier previews showed rapid adoption, and the beta added search cards, notes, texting mode, deep dives, and incognito mode.
"“There's an inherent tension between replying quickly and taking the time to compose thoughtful responses. A slower response is usually more correct, but it can also feel unnatural if it takes too long.”"
"Sesame claims to have built fast search and retrieval systems, so the AI can have up-to-date information, as well as technology that allows it to run multiple parallel searches while speaking, weaving those results into its responses as it talks. That means the AI will talk more like a human, even pivoting mid-sentence if need be, as it taps into newer information - as a human might when remembering another key fact or point they want to add."
"The app offers four distinct AI agents called Maya, Miles, Simone, and Charlie, each of which have their own distinct voice, personality, point of view, and memory. Maya and Miles were previously available in Sesame's Research Preview of its technology, where they were soon accessed by over a million people within the first few weeks, said Sesame investor Sequoia at the time."
"During the beta, Sesame learned from user feedback and rolled out features including search cards with image results for visualizing concepts, notes for capturing takeaways, a texting mode for those times when speaking aloud is not an option, and support for deep dives where you can get more in-depth results. There's also a new incognito mode for private con"
Read at TechCrunch
Unable to calculate read time
Collection
[
|
...
]