@localghost

–

27 November 2023 2h54

storage is local + cloud inference for everything else. trying to figure out something scalable for that second part

27 November 2023

Swift LPC Algorithm Open Source Release for On-Device Speech

By

–

27 November 2023 0h54

We're releasing an open source Swift implementation of the LPC algorithm for on-device speech analysis. Uses Accelerate.framework and runs 2.75x faster than librosa on an M1 Pro! One of @hyperonline_
's first open source repos and a key part of our on-device pipeline for avatars:

27 November 2023

From Torrent Seeds to Decentralized AI: Twenty Years of Sharing

By

–

26 November 2023 22h18

> Year 2003: Seeding torrents for decentralized file sharing. > Year 2023: Hosting an LLM for decentralized intelligence sharing.

OpenRouter Integration Option Under Consideration

By

–

26 November 2023 21h52

not yet. thinking about openrouter, or at least an option for it

Voice AI Latency Optimization for Better User Experience

By

–

26 November 2023 21h45

yeah, could be faster but there’s also a few second delay in there for comfort when speaking. If it fires right after you go silent it can feel frustrating

OpenHermes 2.5 Integration in Decentralized AI Platform

By

–

26 November 2023 21h08

Hopping on a call and going on a walk with with OpenHermes 2.5 by @Teknium1

The energy around decentralized AI is exciting. Adding more open source language models to @apolloaiapp and figuring out a path to release soon. pic.twitter.com/nnnezJVtB4
— Aaron Ng (@localghost) 26 novembre 2023

Hopping on a call and going on a walk with with OpenHermes 2.5 by @teknium The energy around decentralized AI is exciting. Adding more open source language models to @apolloaiapp and figuring out a path to release soon.

I’ll Move Every Electron Myself If Necessary

By

–

26 November 2023 2h24

i'll move every electron myself if I have to

Turbo Button Returns: Computing Innovation Resurfaces

By

–

26 November 2023 2h17

it's time for the turbo button to make a return

LLM Mastery Accelerates Learning Speed Tenfold Productivity

By

–

25 November 2023 10h23

Learning how to use an LLM properly throws you into the top quartile of productivity so fast. It’s like a learning accelerant. A whole new generation is already learning at 10X speed while the last generation is still debating if it can do anything at all.