Truly disappointed @opencode !
Even after getting opencode go subscription just to experience faster Ox Alpha, but it worked slow as hell!
I am never gonna buy your subscription again! This is truly ridiculous
I had an important thing to do, and that’s why I bought subscription only to experience this failure!
All thanks to you! Couldn’t submit on time!
What started as “how fast can we make a grounded voice RAG system?” turned into Anvaya 🎙️
We (me and @sankalphs) experimented with retrieval, streaming STT, guardrails, extractive fast paths and model fallbacks to get here.
Live demo 👇
https://t.co/4isZGZ2twv
Still a lot to improve — but pretty happy with what we built :)
#RAGInGoa
Built Avvaya 🎙️ — our (me and @sankalphs ) attempt at making voice intelligence actually fast, grounded, and useful.
Speech → retrieval → guardrails → the right answer, with a hybrid pipeline designed around latency + reliability.
Try it live 👇
https://t.co/4isZGZ2twv
Would love your feedback :)
#VoiceAI #RAG #AI #RAGInGoa
I started to think if Ox Alpha is actly composer 3, post trained on GLM 5.2!
Since many people saying it’s tokeniser matches with GLM models…..
What do you think🤔 ?
@patloeber Broo stop patting your own shoulder 😭
Relative to other frontier models? Not yet😭
But yea keep on trying, dont lose hope, but please dont praise your own model when its not that good!