BK

@ionleu @AnthropicAI

drop ur startup link

@filicroval What did you mean by "new repo"?

GitHub acaba de matar el vibe coding? Su nuevo repo spec-kit ya lleva 92k estrellas, y muestra hacia dónde va de verdad el desarrollo con IA. Esto es lo que hace: En vez de pedirle a tu IA "hazme una app de tareas" y rezar… ejecutas 6 comandos que convierten tu idea en una especificación estructurada que el agente puede ejecutar: /speckit.constitution → define las reglas del proyecto (calidad, testing, UX) /speckit.specify → describe QUÉ construir (no la tecnología) /speckit.clarify → la IA hace preguntas para eliminar ambigüedades /speckit.plan → ahora sí, eliges el stack /speckit.tasks → genera una lista de tareas ordenada por dependencias /speckit.implement → el agente lo construye El entregable ya no es el código. Es una especificación viva que tu IA lee, discute y ejecuta. Funciona con Claude Code, Copilot, Cursor, Codex, Gemini y 25+ agentes más. El cambio que casi nadie está viendo: "La IA escribe código" → "La IA ejecuta una especificación." El desarrollo centrado en la intención es el nuevo estándar.

@indrazulfi Untung udah pake Electron hihi

Moving agentsOS to Electron, leaving Tauri. 🥲

@querndev @urugothor @hxxwhite A general demonstration of how Quern works will do. I would like to try it myself, but I'm in the middle of exploring other stuffs. Super hectic ✌️

@MainActorDev @urugothor @hxxwhite Good question. Anything in particular you want to see demonstrated? Quern is AI-first and doesn’t have a UI. It’s your agent’s window, and your simulator (or video stream of a real device).

10 phones. Every PR. 3 minutes. No flaky scripts. Just natural language. This is mobile CI now.

@querndev @urugothor @hxxwhite Where is the demo? First impression matter.

@urugothor @hxxwhite Check out Quern for a free, local option. Great for solo devs and small teams.

I just love debugging with Claude.

The hardest bug in iOS development is when the bug is only happen on particular iOS version.

@0xPaulius @getkomand Is that only working on Expo apps? Or Swift and Kotlin also?

@MainActorDev @getkomand You mean an iOS komand app?

Claude design is great... but it can’t design like this:

@0xPaulius @getkomand What about native iOS/Android?

This is my app @getkomand - run codex/claude code/kimi on a codex-style UI

@indrazulfi Ajarin ust

Benchmarkingnya pindah dari SWE-Bench ke Terminal-Bench. Testing the first 20 cases. Yang aku pahamin si SWE-Bench itu emang mustahil 100%, Jadi benchmark si Codex dan Claude setinggi itu, emang jago sih yang bikin model dan harnessnya.

@indrazulfi Lagi bikin hal yang sama tapi lebih niche.

Aku release public beta dulu yak. 😆 AgentsOS, single place to dispatch "any" coding agents, Works with Codex, ClaudeCode and Opencode. Feel free untuk cobain appsnya download disini: agents-os.dev Feedback, Feature Request are very welcome in our discord.

@jazzychad Nowadays, you don't really need to open Xcode at all 😃

displaying the Xcode welcome screen spikes the GPU usage to 50%

@mayaWSB80 @IksiaArt @MiddleEast_Eng The courier did pay first. Do your research properly.

@IksiaArt @MiddleEast_Eng Yes CoD. If non-acceptance means the buyer does not pay. It does not mean the driver pays first. Driver jus return the parcel.

An Indonesian girl works as an online salesperson. One of her customers ordered an expensive item, but when it was delivered, he refused to accept it! 😳 But a man saw her on the street, asked her why she was crying, and then comforted her.❤️

@mayaWSB80 @MiddleEast_Eng Yo, customer can pay in cash

@MiddleEast_Eng This is Grab. She does not bear the cost of the item. Is the Seller that bears the non-delivery. Is this a joke?

I'm building a niche agent for an autonomous end-to-end iOS development. Ralph is the best concept for the agent loop. Let's see where this takes me. github.com/snarktank/ralph

I'm putting GPT5.5 to the test

@twostraws Do a demo!

After months of work, my new app is finally available to preorder on the Mac App Store. It's called Kickstart, and it has just one job: to help indie app developers make more money on the App Store. How does it do that? Let me explain…

@twannl @rocketsim_app Don't we have iPhone Mirroring?

Don't tell anyone: physical device support is coming to @rocketsim_app

@Kimi_Moonshot Can anyone really vouch for this?

Meet Kimi K2.6: Advancing Open-Source Coding 🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2) What's new: 🔹Long-horizon coding - 4,000+ tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization). 🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP + Framer Motion, Three.js 3D. 🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100+ files. 🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops. 🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop. - K2.6 is now live on kimi.com in chat mode and agent mode. For production-grade coding, pair K2.6 with Kimi Code: kimi.com/code - 🔗 API: platform.moonshot.ai 🔗 Tech blog: kimi.com/blog/kimi-k2-6 🔗 Weights & code: huggingface.co/moonshotai/Kim…

@kanavtwt I actually never bought this shii. But I'm gonna give it a try.

Kimi 2.6 JUST dropped: > beats gpt 5.4 and opus 4.6 > 3-5x cheaper > is open source