
Building with voice šļø š§ Repeat founder ($1.5b exit @numeratorone), skier (@onthesnow), data junkie, new dad, @alliebrelig's sidekick, hook 'em š¤
San Francisco, CA
Joined May 2008
- Tweets2.4K
- Following664
- Followers697
- Likes468
Claude could use a little more steering from Dieter Rams.
Every copy/design/ui prompt I now suffix with āless is more.ā
the more I build with voice, the more I prefer subtle audio cues are over voice affirmations in key moments
faster, smoother, less annoying.
600ms sound bite > 11labs voice āthank you, give me a moment.ā
Meta about to take a big bite out of AirPods.
Iāve completely swapped my usage, glass speakers shockingly good for calls.
Ok ok. Iām drinking the Instinct koolaid.
Itās tackling items I donāt want to do⦠but havenāt even told it about.
Jon Brelig retweeted
Much has been said by racists, politicians, and racist politicians (like Bo French) about Indians and UT Austin admissions. I thought I should shed some light so their racism could be slightly more intelligent.
I'm a brown kid. I grew up in Frisco, went to a massive Texas high school, and went to UT.
I would wager that the kids in this picture and I have practically the same background. Like me, they probably went to a massive, pressure-cooker suburban Texas high school, and survived the gauntlet to earn their admissions.
These arenāt foreigners. State law requires 90% of UT's freshman class to be Texas residents. 75% of those in-state seats go to automatic admission on class rank. These are Texans.
Texas, for better or worse, is one of the few meritocratic college admissions schemes in the country for a school of its caliber. The rules are simple. Today, the top 5% of a public school's graduating class is automatically accepted. There is nothing to game. You canāt fake being a competitive rower or have some consultant write your essays for you. There isnāt anything to steal; itās all there on the table to compete for.
And the competition starts the moment the bell rings for your first period of freshman year. You are ranked in your class every single year, for us, #1 to #450. You knew exactly where you were, exactly how hard you had to compete. My year was even less competitive than it is today. The top 6% made the cut, so thatās an all-out war for ~27 kids to get auto-accepted into UT.
So we worked our butts off. Here's what my life was like, starting in kindergarten.
Every summer, before the school year started, I had to finish the upcoming year's math textbook.
I sweated over getting As, even in elementary school. One funny memory is walking to my parents' room, crying, to report my first-ever 89 on a report card.
I did Kumon, my least favorite thing in the world. I still hate that weird half-smile that is their logo.
I went to math and science competitions, where I always lost, and came home crying again. (Quite the crybaby, wasn't I!)
And everyone else around me worked just as hard. Actually, a lot of the kids worked much harder. I know people who took extra classes (zero period) just to boost their GPA. Who routinely slept 5 hours a night to nail every assignment they had after band practice. Who were distraught when they got a 98 instead of a 100. People who stopped doing things they loved, like sports or arts, because those classes dragged down their GPA.
People put their entire life force into getting into this school.
I wasn't even in the top 10% of my class. The competition was too good. I wasn't disciplined enough to hang with them. I got in as one of the 22.5% of admits who are at-large Texans.
These are American kids who earned their way into this school in the most American way possible. Competition. They were told the rules, they competed, and they got the number. And on Saturday they were in that stadium in burnt orange, screaming their heads off, like every other Texan at DKR or around the country. I canāt feel anything but pride for them. That they get to live the dream that so many of us dreamt growing up!
Kids like this have helped improve UTās standing on the national stage. They made it out of the pressure cooker and placed well in Finance, Big Tech, and more recently, startups. They meaningfully contribute to the economies of our state and country. You should be proud of them too.
Overall, this seems like a meritocratic (albeit flawed) way for Texans to be admitted to our stateās flagship school. Itās racially blind. But politicians like Bo French are asking for something different. They want the student body to rebalance racially.
Surely they arenāt advocating for affirmative action, are they?
Managing infra sucks.
Supabase, Vercel, Render, etc. made infra infinitely easier for us old developers.
But the inbound tsunami of claude code developers don't want to manage any of it. Feels like we're due for another turn of the abstraction crank.
Claude and ChatGPT can already write you an app. Getting it live is another story.
Today we're fixing that: connect @floothq, and you can build and ship real apps directly inside Claude and ChatGPT - on the web, in the desktop apps, or from your phone.
The model you already pay for writes and debugs the code, shows you a live preview, and publishes to your own domain. No git, Vercel, Supabase, Resend or OneSignal to set up - a stack of tools that was never built for you anyway.
And the part we're most excited about: Floot doesn't charge you AI credits.
Every message, every change, every random question uses the Claude or ChatGPT subscription you already have. No need to settle for a lesser model to make the credits last!
Why we're doing this: We started Floot to create the easiest and most powerful way to build with AI. Model constraints in 2025 meant you had to wrap AI APIs with careful engineering to get great results. Since then AI has advanced tremendously and no longer needs that wrapping. ChatGPT and Claude can use Floot to build end to end now, and the providers can give you the most economical and powerful AI directly - so we pass that along. You should get the best AI at the price you already pay, and spend your attention on the app, not the meter.
Takes a minute to connect. Free to start: floot.com
trying to converge on my blueprint for scaling out non-eng agent orchestration. Notion has been my stateful source-of-truth for each project where agents work in a loop and delegate tasks and document findings. But the notion MCP is killing me, doesn't even support delete db records.
What is everyone using for non-eng agent coordination... markdown files? linear?
Simultaneous listen/speak Ā š
Conversational voice in need of a step-function improvement to reach the masses, zero room for error and needs to feel effortless. memeburn.com/openais-chatgptā¦
Huge congrats to @spc on Fund III!
No better community for founders figuring it out from day zero
1/ Weāre humbled to announce @spc Fund III: $275M to support exceptional founders from day -1.
Since 2016, weāve had a simple thesis: greatness is more likely to emerge when high talent density meets high curiosity. That's why we focus on -1 to 0.
end-of-turn detection oddly very difficult problem to solve in conversational voice ai. Big props to the team at Daily for open sourcing this
Open source, native audio turn detection ššš
Most voice agents today do turn detection by waiting for speech pauses of a specific, short length. That's not how humans do turn detection when we talk to each other!
I've been working with some friends on a new turn detection model. If you're interested in this problem or in learning more about ML engineering, come hack on a small model with us!
More details below.














