andré

thank you @kotlin

Android AppFunctions 🤝 on-device MCP You can create self-describing functions using the AppFunctions Jetpack library to let assistants like Gemini execute tasks via natural language. Connect your app to AI agents with Android AppFunctions → goo.gle/3NnYBVN

@niklas_wortmann @jetbrains ACP is really good

Friendly reminder that you can use Composer 2 also in @jetbrains IDEs thanks to ACP 🔥🔥🔥

🚨NEWS: Cursor’s $50B “in-house model” is literally Kimi K2.5 with RL on top. Got caught in 24 hours >be Moonshot AI >spend hundreds of millions training Kimi K2.5 >1 trillion parameters, 15 trillion tokens, agent swarm architecture >beat GPT-5.2 and Opus 4.5 on real benchmarks >open-source it because you believe in the ecosystem >one condition: display “Kimi K2.5” if you make over $20M/month from it >Cursor takes the model >runs RL on coding tasks >ships it March 19 as “Composer 2” >blog post: “continued pretraining + scaled reinforcement learning” >zero mention of Kimi K2.5 >“our in-house models generate more code than almost any other LLMs in the world” >publishes benchmark chart >Composer 2 against Opus 4.6 and GPT-5.4 >uses the chart to justify raising at $50 billion! >less than 24 hours later >kimi dev intercepts the API response >model ID: kimi-k2p5-rl-0317-s515-fast >they didn’t even rename it >Moonshot head of pretraining runs tokenizer test >confirms: identical to Kimi’s tokenizer >publicly tags Cursor’s co-founder: “why aren’t you respecting our license?” >two more Moonshot employees post confirmations >all three posts deleted within hours >legal is now involved >but it gets worse >Cursor had Kimi K2.5 listed as a FREE model in their UI just weeks ago >users were openly using it >Feb 9: “K2.5 was in my model list. I updated and it vanished” >it vanished because Cursor pulled it from the picker, and relaunched it as their own model >Moonshot valuation: $4.3B >Cursor valuation: $50B Absolute state of Cursor.

🛠️ Swift Package Manager support is now available in Kotlin Multiplatform. Try importing iOS dependencies from Swift packages or migrating from CocoaPods. See how to try out this experimental feature ➡️ kotl.in/kmp-swiftpm-im… Share your feedback ⬇️🧵

if your skill depends on dynamic content, you can embed !`command` in your SKILL.md to inject shell output directly into the prompt Claude Code runs it when the skill is invoked and swaps the placeholder inline, the model only sees the result!

RT @RxJava: RxJava 4.0.0-alpha-5 released!🤘 💿or'd 🗨️ discord.gg/JUUkTCQbgf Changelog 🫴 github.com/ReactiveX/RxJa… 🫡 @akarnokd

need some good samples of using Tink with Android

@Jack_Timonen yes

@itsandreramon Have you written an instruction to Claude.md to use those proper skills?

so tired of claude code always making quick fixes without understanding root issue or simple dependencies even with proper skills, docs etc. i point it out, then it responds "you're right".

Kotlin for Jetpack Compose. developer.android.com/develop/ui/com…

friendly reminder that you can use @cursor_ai through @JetBrains AI Assistant in @AndroidStudio to get the best of both worlds

Blogged: Syncing Your AI Guidelines Across Workflows. Got tired of repeating my coding preferences to different AI tools, so I’m using a Git hook to sync all guidelines into my repos. This keeps my IDE, CLI agents & CI bots on the same page. saurabharora.dev/posts/syncing-…

@JohnnyNel_ i would say i have fairly detailed docs the model could check, yet it always takes the easiest route. kinda like a lazy human that does things just to complete them and then waits until someone complains.

@itsandreramon learned this the hard way... AI needs constraints upfront, not fixes after. clear boundaries = way less back and forth

Matt Maher tested frontier models in Cursor v. other harnesses. Cursor boosted model performance by 11% on average: Gemini: 52% → 57% GPT-5.4: 82% → 88% Opus: 77% → 93% His benchmark measures how well models implement a 100-feature PRD. @cursor_ai consistently outperformed.

Kotlin 2.3.20 is out, with cool new features like name-based destructuring. We also have a revamped structure for its what new page, check it out and tell us how you like it! kotlinlang.org/docs/whatsnew2…

someone using kotlin-lsp VS code extension with @cursor_ai? does it work? github.com/Kotlin/kotlin-…

Isn't it beautiful to watch? Compounding.

this is insane. just toggle this button and any coding agent can use your browser > no more Chrome extensions > One button, connect Claude Code to your browser all you need is the right harness... try it with the Browser Use CLI right now!

Looks like we'll be doing RxJava 4 with Java 26+ upgraded features and interoperability to many nice things. RxJava 3.x is stable, only minor issues we can only fix with 4 as it seems. Too disruptive. No major or critical bugs. No releases of any kind is expected for the 3.x in the next 2 months and I'd ignore the snapshots of any versions that might come out. Feel free to open a new issue with [4.x] in the title regarding any of your grievances. There is a chance we can fix them now. 🫡 @akarnokd