O P P A (オッパ)

i make it known i don't much like gifts. i made it known i did not much like this gift. she laughed and said, i know. she watched me spray the mister. she watched me heed the sun. she watched the real plants all die off. she did not say a thing

one time a friend got me a succulent. a tiny perfect one in an open dome habitat. i resented the burden. you can't kill a gift. i heeded sun. i got a mister. confidence grew. i got more plants and misted them too. one day i see mold. i scrape it off, alarmed. the plant is plastic

Introducing Durable. The first AI business builder that replaces your 9-5 income. RT + comment “Durable” and we'll build your business for FREE.

Been thinking about this a lot (and prototyping). Rough thoughts on how I think conversations should work; brain-dump for sake of sharing: - Tree data structure, nodes have parent IDs - Threads can either trace full path to conversation root or summarize from "branch" point - Threads can have threads, inf recursive - Agent still sees linear conversation (path to root or summary) - Threads are first-class primitives with their own metadata (name, purpose, etc), not just implicit from tree - Threads can run in parallel: agents can do work in multiple threads simultaneously - Messages have sender identity, not roles: "user" / "assistant" is a two-player limitation IMO - Messages can reference other messages and threads by ID: agents can cite, link, and build on each other's work - Events are the source of truth (very actor-model coded); messages and threads are derived views - Tool calls for creating, reading, and summarizing threads - Compatible across providers, of course --- I also have some ideas around multi-agent participation, state machine-driven agent behavior, & structured conversation flow that make this significantly more interesting

By this weekend, xAI will have three Grok Build models in training simultaneously