Amazing week. Was great to see everyone! If you missed it - here are some great pictures from @jmeistrich

In case you ever wondered how to scan that QR code with your Simulator 😉

This is such a good post. orchidfiles.com/im-tired-of-…

It's App.js week again. Who is already in town?

The moment you see claude calling git reflog and you know it's going to be a fun rest of the session

We just cut the SDK 56 beta 😅 ◆ 50% faster iOS builds (precompiled XCFrameworks) ◆ 40% faster cold starts on Android ◆ Expo UI is stable ◆ iOS widgets are stable ◆ expo-router rebuilt from scratch ◆ Inline native modules ◆ Brownfield multi-app support The obvious themes are speed and stability. But there are a lot of other interesting changes (like Expo Router decoupling itself form React Navigation). Get all the nuance and detail in the changelog below ↓

Just caught Claude trying to dump session tokens to an object passed around the whole web app. Ability to review PRs remains a competitive advantage.

本日のお浸かり 皆さま　本日もおつかりさまです

My brain is fried this week from trying to solve some of the complexity LLMs are generating to little success. At this moment in time it definitely feels like writing software is _harder_ in many situations. More taxing mentally.

People ask me what's my secret for not running out of tokens. It's simple. My Claude finds the slowest CI command that it can run locally and runs it 5 times with random combinations of | tail -n and head that tell it nothing until it gives up and runs the full thing.

What MCP do you all use for giving claude hands and eyes for use in iOS simulator?

Introducing Expo Agent Build truly native iOS and Android apps from a prompt. Anything from React to SwiftUI to Jetpack Compose. Compile and deploy for Apple, Android, and the web right from the browser!

Exactly one year ago (10 mar 2025), Dario Amodei: "I think we will be there in 3-6 months, where AI is writing 90% of the code. And then, in 12 months, we may be in a world where AI is writing essentially all of the code." This turned out to be... too darn accurate.

Not sure if I managed to mute all agentic coding grifters or they had to return the stacks of mac minis before the deadline

Last week I accidentally went to sleep at 10pm and woke up at 6am rested like never before but my body didn’t fall for it and we are back to 4am scrolling I guess

You know you are not getting anywhere today with your problem when chatgpt quotes your stackoverflow question from 2y ago as the main source

openclaw is great and use it too - believing you need to buy mac minis and run simultaneous agents on different hardware to replace employees (which is complete bs) means that you have lost touch with reality

No amount of LARP-ing gets anywhere close in efficiency to just talking to the LLM There's probably a normal distribution meme about this