Joined September 2007
160 Photos and videos
Constantly amazed at how realistic and clever @interaction’s Poke is. Really unlike anything else
2
1
26
2,378
I’ve been on @getcasa since the start of the year and it’s my #1 new product this year by a mile. Total life changer, seriously.
Apr 30
After two years of building under wraps, today we're announcing Casa – your personal property manager. We've raised $27M to redefine the homeownership experience from the ground up. We believe your home is your most treasured asset, emotionally & financially. It shouldn't also be a second job. Most homeowners are on their own – expected to have the time, expertise, and relationships to keep things running. Finding a plumber you can trust. Remembering when the HVAC was last serviced. Knowing what's actually wrong before someone shows up to fix it. Casa gives every homeowner what used to be reserved for the few: a dedicated team that knows your home deeply, handles the work, and stays in your corner. We're enabling this by building a deep, technical understanding of every home we serve – something that's never existed before, across 100 million single-family homes in the country. For $199/mo, membership includes: - A complete inventory of your home, built using specialized hardware & software - 1.5 hours of handyman time every month (and it rolls over) - Unlimited Concierge requests to take on virtually any home project - Custom, proactive care plans built specifically for your home - Weekly package and donation pickups - Scheduling and payments for your regular vendors - Utility and property tax monitoring …and we’re just getting started, with more benefits on the way to make the experience of owning your home as magical as it always should have been. Available now in the SF Bay Area and Los Angeles. Reserve your spot everywhere else. → getcasa.com
5
3
33
9,250
Ben Cherry retweeted
Since livekit-wakeword release, the number one question we’ve been asked is if we support wake word in other languages. The answer is yes. By leveraging VoxCPM2 from @OpenBMB, we can generate samples in 30 languages and train on them. All local. All in a single command. All open-source.
Apr 16
We launched livekit-wakeword, an open-source library that lets you train a custom wake word model from scratch with a single command. It handles synthetic data generation, augmentation, training, and ONNX export all in one shot.
1
4
22
3,011
Ben Cherry retweeted
if you have tried to train a wake word model before, you know the pain today we are open sourcing livekit-wakeword, a tool that lets you train production-grade wake word models with a single command on any platform compared to openwakeword, livekit-wakeword achieved dramatically better results across every metric: > 100× fewer false positives per hour > 60× lower detection error > 86% vs 69% recall this is thanks to our improvements with the data generation pipeline (diverse samples and config options), training pipeline (focal loss and label smoothing) and model architecture (attention) a big bonus: models trained with livekit-wakeword are fully backward compatible with openwakeword, so you can drop in our wake word models into your existing @home_assistant setup or any oww project check it out here github.com/livekit/livekit-w…
5
12
100
5,965
Ben Cherry retweeted
Introducing Agents UI, an open-source @shadcn component library for building polished React frontends for your voice agents. Audio visualizers. Media controls. Session management tools. Chat transcripts. All wired to LiveKit Agents. Install via the shadcn CLI and own the code.
38
98
1,293
182,504
Ben Cherry retweeted
This decision makes America less safe, today and tomorrow. Pete Hegseth just told the entire U.S. tech sector: don't make a deal with the U.S. military because my next meltdown might mark you as more dangerous than China. It turns out, nothing is undermining our military capabilities more than Pete Hegseth and Donald Trump's fragile masculinity.
This week, Anthropic delivered a master class in arrogance and betrayal as well as a textbook case of how not to do business with the United States Government or the Pentagon. Our position has never wavered and will never waver: the Department of War must have full, unrestricted access to Anthropic’s models for every LAWFUL purpose in defense of the Republic. Instead, @AnthropicAI and its CEO @DarioAmodei, have chosen duplicity. Cloaked in the sanctimonious rhetoric of “effective altruism,” they have attempted to strong-arm the United States military into submission - a cowardly act of corporate virtue-signaling that places Silicon Valley ideology above American lives. The Terms of Service of Anthropic’s defective altruism will never outweigh the safety, the readiness, or the lives of American troops on the battlefield. Their true objective is unmistakable: to seize veto power over the operational decisions of the United States military. That is unacceptable. As President Trump stated on Truth Social, the Commander-in-Chief and the American people alone will determine the destiny of our armed forces, not unelected tech executives. Anthropic’s stance is fundamentally incompatible with American principles. Their relationship with the United States Armed Forces and the Federal Government has therefore been permanently altered. In conjunction with the President's directive for the Federal Government to cease all use of Anthropic's technology, I am directing the Department of War to designate Anthropic a Supply-Chain Risk to National Security. Effective immediately, no contractor, supplier, or partner that does business with the United States military may conduct any commercial activity with Anthropic. Anthropic will continue to provide the Department of War its services for a period of no more than six months to allow for a seamless transition to a better and more patriotic service. America’s warfighters will never be held hostage by the ideological whims of Big Tech. This decision is final.
14
30
342
12,252
Claude is the best coder in the world and a true patriot. Anthropic is winning 2026 so far.
A statement on the comments from Secretary of War Pete Hegseth. anthropic.com/news/statement…
1
234
RT @Acosta: The only thing more powerful than hate is love. ¡Que bueno Bad Bunny!

3,519
Ben Cherry retweeted
Replying to @ycombinator
Hey @ycombinator & @amiklas… we heard you’re looking for us 👀 We’d be happy to show you what we’ve built so far, and we may even have a little room left in the round. 😉 DM and check out trydotted.com
17
22
664
Ben Cherry retweeted
This is absolutely shameful. Agents of a federal agency unnecessarily escalating, and then executing a defenseless citizen whose offense appears to be using his cell phone camera. Every person regardless of political affiliation should be denouncing this.
Drop Site obtained harrowing footage of the latest killing which appears to be from the perspective of the woman in pink filming from the sidewalk
245
947
8,364
980,778
Very cool to be part of this - honestly amazed almost every day by how much people love voice AI and especially how much they love using LiveKit to build it.
Jan 22
We learn to speak before we learn to read. Voice is the most natural interface we have. We just raised a $100M to make building voice AI as easy as a web app.
2
235
Ben Cherry retweeted
Love love love @livekit's example repos. Every developer should have a docs MCP and instructions on how to set it up. And look at those AGENTS and CLAUDE md files
1
1
4
616
Ben Cherry retweeted
15 Sep 2025
Join us on 10/1 at 5:30p for the first Physical AI Meetup hosted by @livekit at @frontiertower. Come for robot demos, panel discussion with industry leaders, food, drinks & networking. luma.com/physical-ai-meetup
1
6
12
6,381
Ben Cherry retweeted
20 Aug 2025
Serverless voice agents are here. Two years ago, we worked with OpenAI to plan the ChatGPT Voice Mode launch. Voice agents were different from web apps: • sessions last minutes to hours • what’s said next depends on what was said before • UX breaks even with moderate latency • CPU/memory usage isn’t uniform Scaling voice agents is more like scaling a multiplayer video game. To do it right, you need tech for load balancing, capacity management, deploying updates, and observability. We’ve seen voice AI devs spend time building this in-house over and over — a clear sign that deployment and scaling are undifferentiated problems. So starting today, you can push your agent code directly to LiveKit Cloud and we’ll handle the hard parts for you. Try it out — and DM me your feedback.
20 Aug 2025
You can now deploy AI voice agents to LiveKit Cloud. We handle: • Stateful load balancing • Capacity management • Draining and instant rollbacks • Operational observability
7
8
70
20,302
13 Aug 2025
super excited about this one
13 Aug 2025
Voice AI is coming to video games. Stellar Cafe is the first multiplayer virtual world where you can talk to other players and AI at the same time. There are no dialog trees, every interaction is unique. Built on LiveKit Agents, the team at @AstroBeamHQ has solved a bunch of hard problems to make multi-party and spatial voice AI a seamless experience.
1
201
13 Aug 2025
The best movie about getting too attached to an AI chatbot isn’t Her. It’s Chamber of Secrets. Ginny Weasley got catfished by VoldemortGPT.
2
177
22 Jul 2025
Can confirm - live avatars from Hedra are 🤯 and really fun to build with, too.
22 Jul 2025
We’ve entered the era of AI agents. Voice may be the interface, but video is the next unlock. Today, we’re launching Hedra Live Avatars, the most advanced streaming avatar model in the world. - Low cost: Just $0.05/min — 15x cheaper than existing solutions - Ultra-low latency: Powered by LiveKit’s global infra with sub-100ms response times - Flexible: Works with your favorite LLMs or TTS models like Gemini or OpenAI - Style-agnostic: Create photorealistic, animated, or stylized avatars from a single starting image Try the demo for free today!
2
275
Ben Cherry retweeted
18 Jul 2025
Agents 1.2 for Python is now released! This includes our new test framework, observability w/ OpenTelemetry traces, half-duplex support (swapping a realtime model's voice w/ your own TTS), significant improvements to end of turn model (now with Hindi) and more! Let's dig in ...
13
26
209
37,248
8 Jul 2025
We need a new word like "typo" for when your code has a small mistake except that it was made by your coding agent doing dumb stuff or hallucinating. I propose "llmo" (pronounced "elmo")
151
3 Jun 2025
if you must vibecode an AI bot that discovers software engineering jobs and applies to them for you I'd at least suggest you don't put it in a public repo at the top of your github profile
1
181