Founder and CEO of @Korey_AI and @Shortcut. We're building a workspace for agents and people to build software together

New York City
Excited to watch everyone here speedrun their learnings about the differences between a $60K/year NYC “preschool” and a normal preschool almost anywhere else.
it's true, these brooklyn teachers are seriously dripped out in issey miyake
1
19
6,386
You should be spending at least half of your tokens improving the software that you’ve already built. Piling on new features without thinking seems to be the scourge of everything I try these days.
3
1
13
1,074
The other day I had someone on street ask me how to get to the F train station. After I told them they said "but Claude said it's the other way." Ok. 🤷‍♂️ theverge.com/report/1002963/…
5
9
711
Sonnet 5.5 is the first non-frontier model we've seen that can score 100% on our project management benchmark Koreybench (and it finishes it 3 times faster than the Sonnet 4.6 did) Just a really great model.
1
1
333
Me: "Remove these models as options in the list" Claude: "I'll write some test cases to show that they've been removed" 🤦‍♂️
3
3
374
Between Opus 5.5 and now Sonnet 5.5 Anthropic is back on a roll. These are both very, very good.
2
1
7
399
Claude just "rerere replayed my earlier bad resolution"
2
222
The correct way to prompt 10 agents each morning.
1
1
5
311
I'm seeing some non-devs start to use sandboxes/Devin/etc to push PRs for smaller production things around the edges. Fixing smaller "this has always bothered me" sort of problems.
Replying to @GergelyOrosz
Bury your head in the ground at your own risk. I aim to not jump on any hype trains, but since Opus 4.6 and GPT-5.2 + the harnesses it was clear that these things can write code nearly as good as I can in my best language; better in other languages. But we won't see non-devs push production code for a long time; possibly forever, if you ask me. Software still needs to be built in robust ways, and it's our profession to do this well, and use the new tools we have, which create new and interesting (+tough!) challenges
1
461
Kurt Schrader retweeted
Shortcut (Formerly Clubhouse) is goated Clubhouse the voice chat app is lame
1
5
210
Obviously.
We asked 25 top VCs: If you could invest in any venture fund started in the last 5 years, what would it be? There was one resounding answer @conviction
1
1
432
I'm not saying that new, super-fast Shazam is the best reason to upgrade to a new Apple Watch, but it's a very good reason. I don't know why Apple didn't talk about it more in their keynote.
293
It doesn't surprise me that AI companies targeting lawyers are one of the big success stories. Lawyers are already used to delegating their work to associates, so plugging in an agent instead is an almost perfect fit. They've already built the muscle.
210
I use several agents everyday, but almost everyone that I invite to use them falls off after a few days. It would be super interesting to see some number behind early usage falloff on these. It's still very early innings.
The problem with all of these AI personal assistant things is that people don’t actually want to do stuff. You fucking get that right? Do you understand that? Just like AI tools in the workforce, AI assistants don’t actually abstract decisions for you, they let you accelerate decision making. So instead of making one decision a day and then lamenting you can’t do more, AI assistants are going to let you make ten decisions a day and act on all of them. A miracle? Nah dog, a fucking nightmare. Nobody except type A strivers who need Twitter fodder actually want that. Let me tell you a story. When I got back from college I was inspired. If I could take on an elite university with grit and determination, so could everyone I know. I was all razzed up to get people I know to achieve their potential. What I learned after many years of trying is that absolutely nobody wants to realize their potential. People want to hang out with friends and complain. That’s how the world has worked for ten thousand years. This weather fucks. Can you believe the cows walked off. People don’t want enablement. People don’t want you to take all of their excuses. TV is mindless passive activity. AI assistants are not. They’re telling people that they can achieve more. And people absolutely do not want that. Let me tell you another story. Once upon a time I lead a big process overhaul at work and it was great. Two years later I hired a contractor to do something similar. But I personally didn’t want to have to do a bunch of work. Within a week I knew I fucked in. This contractor kept coming to me with decisions I needed to make. Dude I wanted to not have to think about this. Again, a helper when you don’t actually want help is a disaster. None of these AI assistants will take off because people don’t actually want assistants.
2
5
340
Kurt Schrader retweeted
🥳 Excited to start revealing what we've been working on in the last few months. First, we decided to reinvent Kubernetes for agentic workloads with statefulness and fast resumption. Secondly, we are building an agentic orchestrator that will be Google's open agentic orchestrator and runtime. github.com/google/ax
127
378
4,239
721,346
Regularly sending smaller but uncached prompts is a great way to explode your costs. This is a cool idea, but it’s fundamentally incompatible with the way that LLMs currently work.
found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant
1
385
It would be interesting to run this loop against a local model and see what the results look like though.
32
So I connect to your company directly via Slack Connect to avoid your support bots, just so that I can talk to your support bots in Slack now? Do I have that right?
229