Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Georgi Gerganov Profile picture
Georgi Gerganov
@ggerganov
24th at the Electrica puzzle challenge | https://t.co/baTQS2bdia
3 subscribers
Feb 24 • 4 tweets • 2 min read
Today I was sent the following cool demo:

Two AI agents on a phone call realize they’re both AI and switch to a superior audio signal ggwave The developers (Anton and Boris) used the ggwave library to make the AIs communicate faster over a phone call

github.com/ggerganov/ggwa…
Mar 28, 2023 • 4 tweets • 2 min read
llama.cpp just got access to the new Copilot for Pull Request technical preview by @github

Just add tags like "copilot:all" / "copilot:summary" / "copilot:walkthrough" to your PR comment the magic happens 🪄 Let's make some PRs to test this thing 😄

Btw, any idea why the Social Preview image is not working on Twitter? I've added a cool logo of the project but it's not showing up for some reason 👇

github.com/ggerganov/llam…
Mar 26, 2023 • 8 tweets • 2 min read
Introducing LLaMA voice chat! 🦙

You can run this locally on an M1 Pro Powered by: ggml / whisper.cpp / llama.cpp / Core ML
STT: Whisper Small
LLM: 13B LLaMA
TTS: @elevenlabsio

The Whisper Encoder is running on Apple Neural Engine. Everything else is optimized via ARM NEON and Apple Accelerate