THIS IS HOW FABLE 5 MOVES WHEN YOUR VAULT IS BUILT RIGHT
direct path. zero wandering. hits the target on the first try.
without structure it's the opposite. 7 files opened. 2 minutes wasted. brief from 3 months ago still missing.
one index file per major folder. gives the agent a direct line to what it needs.
same task dropped from 2 minutes to 10 seconds. same model. nothing else changed.
build the path or watch it search in the dark.
full breakdown in the article below ↓
@icelabaratory Подождем сол от жпт, там посмотрим кто выиграет, но по качеству на аналитических задачах уровень сильный, но меня смущает что тот же опус по признанию самого фабля работает лучше с текстами
Ladies and gentlemen, it’s here:
I’m proud to announce that 'Nexus' will be my upcoming hybrid feature film.
Here is a 5-minute teaser, made by 3 people in 2 weeks.
Made with Dreamina AI using Octo & Dreamina Seedance 2.0, full workflow coming soon
Roadmap:
1. Better agent integration: We'll improve shadcn/skills and continue making the CLI more agent-friendly.
2. Full theming support: We'll look into a theme editor with custom colors and see how we can extend preset code to support custom themes.
Thanks everyone.
Formisch is now in the official shadcn/ui forms docs ⚡️
Schema-first, fully type-safe, headless. Works with Valibot out of the box — no resolver, the schema is the source of truth.
If you're building forms in @reactjs with @shadcn, give it a try: https://t.co/l7xPMebacg
A few quality-of-life improvements for registry builders:
• `include` for organizing large registries into smaller files
• `shadcn registry validate` to check your registry
• loaders for serving registries dynamically
Check the changelog on the site.
Google acaba de publicar el estándar de Code Review que usan sus ingenieros internos.
Literalmente puedes darle esta documentación a un agente de IA y convertirlo en un revisor de código con estándares de Google.
La mayoría de IAs solo generan código.
Ahora también pueden:
→ detectar malas prácticas
→ revisar arquitectura
→ pedir cambios útiles
→ validar legibilidad y mantenibilidad
→ dar feedback estilo Google
El documento incluye cómo revisan código realmente dentro de Google:
→ criterios de aprobación
→ qué bloquea un merge
→ cómo escribir código fácil de aceptar
→ términos internos como LGTM y CL
No es teoría.
Es el sistema real que usa Google para revisar millones de líneas de código.
Enlace abajo 👇
Если вы увидели оригинальный пост и подумали - "О чем вообще речь, нихрена непонятно" то вы не одиноки, я сам офигел, за 2 года некоторые вещи выветрились напрочь у меня самого.
Бахнул Concurrency Mindmap для более комфортного погружения. Исходник добавлю ниже.
🚨 son dakika : google - aslında cidden en zor olan dev ops ve claude için yapılması ve öğrenilmesi gereken zorlu görevleri direkt skill olarak yayınladı💰
ata now fits into the frameworks you're already using:
fastify-ata and ata-vite as dedicated plugins.
recipes for hono, elysia, trpc, tanstack form, express, koa, nestjs, sveltekit, and astro, 10-20 lines of glue each.
one validator, every stack.
for use:
https://t.co/ZfNUUJhoXa
Someone just open-sourced a tool that makes Claude Code 90% cheaper.
It sits between your AI and the shell and compresses command outputs before they hit context. git push, cargo test, ls, grep.. all auto-rewritten.
works with Claude Code, Cursor, Gemini, Codex, Copilot.
100% Open Source.