dsa

8.7K posts

dsa

dsa

@dsa

early yc, early twitter, early 23andme, late bloomer @livekit

future Katılım Ağustos 2007
327 Takip Edilen10.2K Takipçiler
Sabitlenmiş Tweet
dsa
dsa@dsa·
Today is a day I’ll never forget. I grew up in Cupertino. My dad was a tech founder in the 80s/90s. I was in YC S07. LiveKit is my 5th company. The first 4 didn’t work out. I’ve had a lot of advantages — it still took 20 years to get here. Founders: keep taking shots.
LiveKit@livekit

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.

English
82
38
931
93.2K
dsa retweetledi
Ivan Burazin
Ivan Burazin@ivanburazin·
The co-founder of a $1B VoiceAI infra company says you can't test agents the same way you test traditional software. According to @dsa, you have to test these things almost like you test human beings. Like college degrees, resumes, job interviews, reference checks, etc. What you're really trying to do is build statistical confidence that the person you're hiring can do the task with 99% precision/confidence. Have to test agents the same way by running thousands of end-to-end simulations. Permute accent, language, system prompt, instructions, etc, and see how it performs against the success criteria spit out by your observability stack. This way, you're building confidence, deploying it, and observing which bugs/issues require tweaking. Take those back and make changes to the agent code. Test again, run simulations, and make sure there's no regression. Then deploy again, scale, and observe. That's how the loop goes.
English
7
3
59
8.1K
dsa
dsa@dsa·
Thanks for having me on, @jason!
This Week in AI@ThisWeeknAI

"Any feature we release, a competitor could release within two weeks." @MatanSF (@FactoryAI) on why the moat isn't software anymore. @dsa (@livekit) on building the framework for voice, video, and physical AI. @gsivulka (@HebbiaAI) on what it takes to win in vertical AI. They join @jason on This Week in AI, Episode 11: 00:00 Intro & AGI debate 03:30 Factory: autonomy for software engineering 04:29 LiveKit: open source to ChatGPT voice 10:31 Hebbia: AI for capital markets 13:21 SpaceX-Cursor $60 billion deal breakdown 26:28 Moats in the age of vibe coding 38:10 Deterministic agents vs. open chaos 45:56 DeepSeek V4 01:05:23 OpenAI's spend problem 01:12:08 P-doom scores

English
1
0
3
656
dsa retweetledi
LiveKit
LiveKit@livekit·
We shipped structured data collection for voice agents. Use data collection mode in Agent Builder, or Tasks and TaskGroups in our Agents SDKs. Every session ends with a clean JSON payload for your CRM, form, or database. Great for lead qualification, patient intake, and surveys.
English
7
6
62
4.5K
dsa
dsa@dsa·
@sama (there is: webrtc)
English
0
0
0
109
Sam Altman
Sam Altman@sama·
feels like a good time to seriously rethink how operating systems and user interfaces are designed (also the internet; there should be a protocol that is equally usable by people and agents)
English
1.8K
787
12.5K
1.5M
dsa retweetledi
LiveKit
LiveKit@livekit·
We published a guide on how to do parallel processing inside an agent session, with policy violation checks and guardrails as the example. Check out the demo and read the full post for all of the code you need to apply this pattern to your voice agents.
English
6
8
65
4.3K
dsa retweetledi
LiveKit
LiveKit@livekit·
xAI STT is live. You can now run a complete cascaded voice agent pipeline on xAI (STT + Grok + TTS) through LiveKit Inference with one API key, giving you more control, full visibility, and easy component swaps.
English
13
12
91
10.1K
dsa retweetledi
LemonSlice
LemonSlice@LemonSliceAI·
We did it! We built the fastest interactive avatar model Introducing LemonSlice-2.1 𝘍𝘭𝘢𝘴𝘩 ⚡ Here’s how we did it using @modal and @livekit 👇 (note: it was not easy)
English
95
57
451
235.4K
Jack
Jack@jackndwyer·
@livekit Will never debug any other way again
English
1
0
4
151
dsa retweetledi
LiveKit
LiveKit@livekit·
We shipped Agent Console, a realtime debugging surface for voice agents. Talk to your agent and see the entire pipeline live, from audio and latency to tool calls, transcripts, and participant state. Available now in the LiveKit Cloud dashboard.
English
11
14
72
11.7K
dsa
dsa@dsa·
@SteveAldrin_ @livekit this is cool, i’m gonna share with the team — maybe smth like this can be folded into the framework
English
1
0
1
149
steve aldrin
steve aldrin@SteveAldrin_·
Voice agents don't acknowledge you while you talk. They just wait. Humans don't. So we built real-time back channeling for voice AI. Check this out 👇 Built with @livekit
English
2
1
8
500
LiveKit
LiveKit@livekit·
Pronunciation is one of the fastest ways to break trust in a voice agent, especially in healthcare, legal, and finance where terminology matters. Rime's Mist v3 introduces phonetic brackets that let you define the exact pronunciation for any word and reproduce it deterministically. We built a demo nurse agent that stumbled on words like "levothyroxine" and "gastroesophageal," then fixed every one with a few lines of config. It's also fast.. as low as 100ms TTFB. Try it on LiveKit Inference today.
English
4
13
102
6.7K
dsa
dsa@dsa·
Today @livekit launched Data Tracks. Physical AI and robotics applications need low-latency, realtime transport for data beyond just audio and video. Data tracks let you transmit binary frames from any source: IMUs, LiDAR, RGBD cameras, control systems with no codec overhead and the same low-latency semantics as media. They support full end-to-end encryption and every frame includes a timestamp, so you can easily align data from different sensors. Excited to see what folks build with this! youtube.com/watch?v=Ju9Jz0…
YouTube video
YouTube
English
1
2
9
6.5K
dsa retweetledi
Daytona
Daytona@daytonaio·
The cloud was not built for AI agents. Recently at @daytonaio Compute Conference, @dsa, co-founder & CEO of @livekit, sat down with @mattturck, VC at @FirstMarkCap to break down why stateful, long-running agent sessions cannot be deployed and scaled the same way as traditional web applications.
English
2
27
34
4.6K
dsa retweetledi
LiveKit
LiveKit@livekit·
Gemini 3.1 Flash Live just dropped and it's available with LiveKit today. This is the first Gemini 3 native audio model on the Live API. Better instruction following, improved tool calling, reduced speaker drift, and support for 70+ languages. Audio in, audio out. No text conversion in between.
English
19
30
290
40.1K
dsa
dsa@dsa·
Binh is building FSD for toy cars
Binh Pham@pham_blnh

day 2 of building a self-driving power wheel today i officially trained a self driving model from scratch and deploy it on the car by just simply brute forcing everything, I: > made a remote tele-op and remote data collection app built on @livekit infra > feat: 60ms e2e latency between the car and inference compute (car and compute in vietnam with singapore sfu) > feat: data is collected on operator side, baking latency into observation space itself (I expect this made the model more robust against latency) > recorded 30 min of data at 30fps and converted the dataset to lerobot (you can check a sample here) > trained a simple ACT model (3 epoch, batch size 8) to drive the car around my house > deployed the model on the car with remote inference the video explains everything shortly reflection: > the model is ofc bad, idt behavior cloning would work at all for such complex task on such small sample size > it did work in some cases where the observation is well within distribution, even generalizes to back the car when it gets stuck up next: > will hack alpamayo (@nvidia) or @comma_ai ’s e2e to somehow fit this > or train with a llm backbone or a locomotion prior to see if it generalizes

English
0
0
3
586
dsa retweetledi
Binh Pham
Binh Pham@pham_blnh·
was gonna do a small data collection and training run today but thought what if i give the raw controls to an agent first (@livekit agent and @Google gemini) did not disappoint lol, it can actually navigate to objects around my room
English
2
2
25
1.3K

Keşfet

@Jason @sama @modal @livekit @jackndwyer @SteveAldrin_ @davidzh @adam_martin