Andrew Riefenstahl

Passionate Musician 🎸 & Web App Developer 💻 || Tech Meets Art 🎨 Mentality "Carving a path less traveled." 🥾 Frontman for the @thelewddudes of Austin, Texas

[Andrew Riefenstahl @Riefer02]

How is he so ahead of his time? This person is literally the only one trying to protect the working class in the United States. He is a true national hero equivalent to Abraham Lincoln, MLK, or Susan B. Anthony.

[Bernie Sanders @BernieSanders]

I will soon be introducing a bill to give the public a 50% ownership stake in the largest AI companies in America.

This would guarantee that the trillions created by AI are used to improve the lives of all of us — and block oligarch decisions that harm the American people.

[Theo - t3.gg @theo]

On this episode, Ben crashed out so I don't have to

[Andrew Riefenstahl @Riefer02]

@MichelleBakels @opencode ATX

[Andrew Riefenstahl @Riefer02]

@jlongster I just tried it again and when I warped into a new worktree, the MCP list on the right side updated, and my locally defined mcp from the project opencode.json were not there. Your right. I would expect them to come over and have them persist.

[Andrew Riefenstahl @Riefer02]

@deepseek_ai Legendary!

[Andrew Riefenstahl @Riefer02]

@thdxr I’ve been using Talon open source speech to text software for a while. I should check out the local models though.

[Andrew Riefenstahl @Riefer02]

@GoDaddy 👏 @TheTweetOfGod

[Andrew Riefenstahl @Riefer02]

@theo Very excited to give it a try. Will accessibility features be first class?

[Andrew Riefenstahl @Riefer02]

@garysheng love it! ty

[Charly Wargnier @DataChaz]

NVIDIA just removed one of the biggest friction points in Voice AI.

PersonaPlex-7B is an open-source, full-duplex conversational model.

Free, open source (MIT), with open model weights on @huggingface 🤗

Links to repo and weights in 🧵↓

The traditional ASR → LLM → TTS pipeline forces rigid turn-taking.
It’s efficient, but it never feels natural.

PersonaPlex-7B changes that.

This @nvidia model can listen and speak at the same time.

It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components.

That unlocks:
→ instant back-channel responses
→ interruptions that feel human
→ real conversational rhythm

Persona control is fully zero-shot!

If you’re building low-latency assistants or support agents, this is a big step forward 🔥

[Andrew Riefenstahl @Riefer02]

@jarredsumner Very cool looking forward to spawning some agent terminals.

[Andrew Riefenstahl @Riefer02]

@jarredsumner Congratulations!

[Andrew Riefenstahl @Riefer02]

@GoDaddy is sh1t! Literally holding my clients website hostage through zero support.

[Andrew Riefenstahl @Riefer02]

@GoDaddy is a terrible product. And I highly recommend that nobody ever use it. Currently trying to get a client off of it last time I tweeted this. It was removed. Customer service is nonexistent and continues to drop support conversation.

[Andrew Riefenstahl @Riefer02]

I moved to Astro for anyone who’s listening lol love it so much more.

[Andrew Riefenstahl @Riefer02]

Where is the @GatsbyJS community? I’ve been exploring the discord, but it seems like a Ghost Town. I honestly am a big advocate for Gatsby and if this project is sunsetting, I’m gonna need some help moving my Front end. #partialhydration #Help @Netlify

[Andrew Riefenstahl @Riefer02]

@GoDaddy is an absolute piece of shit hosting provider. Speaking for a client friend.

[Andrew Riefenstahl @Riefer02]

@deno_land Very excited to give it a spin!

[Andrew Riefenstahl @Riefer02]

@thsottiaux This is awesome thanks a lot! I just made a home rolled version of putting Codex in an action and doing context aware code review.