Laserdisc Librarian

lo-fi spy: video, steganography, and you youtube.com/watch?v=2y0Qj0…

🚀 New OpenInference integration with @pipecat_ai We’ve added OpenInference instrumentation for Pipecat using OpenTelemetry. Pipecat services can now emit standardized traces and spans with semantic context across realtime agent pipelines. The integration instruments: 🔹agent execution 🔹tool / function calls 🔹model interactions 🔹service and pipeline boundaries Traces follow OpenInference conventions and can be inspected in @ArizePhoenix for debugging, performance analysis, and understanding execution flow in production. 🎥 Demo below

Welcome back to 1998. Call up these 12 cuties using the cordless phone your parents let you take into your bedroom (sometimes) and figure out which one has the hots for you. <3 You can call these phone numbers for realz, home skillet. Or just clone the github repo and get jiggy. And if you come to the voice AI hackathon tomorrow, oh, snap, you might win some phat prizes. (And don't tell me I got the slang wrong. I was there.)

hack the git, son always `git rebase main` (feature) $ git checkout main (main) $ git pull --rebase origin main (main) $ get diff origin/main => should print nothing (main) $ git checkout - (feature) $ git rebase main (feature) $ git push origin feature c.tenor.com/EajrLApNoIYAAA…

Voice agents + MCP ... When I watched this code walk-through from @vipyne, I thought "wait, why didn't she edit out the LLM making those mistakes at the beginning ... oh I get it, good demo!" Vanessa shows how to use multiple MCP servers via the new `MCPClient` class in @pipecat_ai and mcp . run from @dylibso.

Be the change you want to see: How to contribute to FFmpeg youtube.com/watch?v=_k64TY…

Developer meetup Tuesday! Join @swyx, @shresbm @GoogleDeepMind, @krandiash @cartesia_, Niamh Stanford, @kwindla @pipecat_ai @trydaily 🍕 🎙️ 🛠️ 🤖

Gemini 2.0 launched today. Amazing multimodal capabilities, long context windows, fast response times, built-in tools, and top-of-the-leaderboards reasoning capabilities. Plus a new API — the Multimodal Live API — for conversational AI applications, like voice agents and multimodal copilots. @Google and Daily have partnered to build Multimodal Live API support into the @pipecat_ai Open Source SDKs for Web, Android, iOS and C++. The Pipecat SDKs come with echo cancellation and noise reduction, device management, event abstractions, React hooks, and more. They support both direct connections to the Gemini WebSocket API, and WebRTC routing on Daily's global ultra-low latency network. Build realtime voice agents with Gemini, Pipecat, and Daily. Links to docs and starter kits in the thread below (1/4)...

I present my speedrun of `Signup to Daily Bot voice assistant deploy.` Silly? yes. Pretty freakin' cool? also yes. Fun? most yes.

don't fall in love with her demo.rtvi.ai

happy fourth to all who celebrate

the feeling when you write a new bash one-liner and it works perfectly on the first try

hot take: think of an llm as a coworker, not a tool. coworkers are great and you trust them, but coworkers are also people and people make mistakes.

santacat.ai something about the internet and cats and ai and destiny... happy holidays, everybody!

@thecodinghigh That sucks. I'm sorry. Cold comfort, but some companies are trying to be more transparent wrt compensation: twitter.com/trydaily/statu…

What's your glitch?: An ode to datamoshing buff.ly/3f93sFK

Omg @vipyne did it. She actually did it.

@inconvergent Is it for sale now...? (asking for a friend)

"the persistence of memory by lisa frank"