Hernan Zaldivar

.Net, web, Indie game and mobile developer & snowboarding lover.
Creator of A Comic of Zombies and @hypstr_app ( game and app for iOs

[Miguel Ángel Durán @midudev]

Se cumplen 5 años desde que se lanzó GitHub Copilot.
Usaba Codex, un modelo basado en GPT 3 de OpenAI.
Parece que fue ayer y, a la vez, una eternidad.

[TIC Educativas💻📱 @TicEducativas]

¡Lleva tu productividad al siguiente nivel con Claude! 🚀 Esta guía completa elaborada por @Ben_escrito es el mapa que necesitas para sacarle el máximo partido: desde el análisis profundo de archivos hasta la automatización con Connectors y Projects.

No es solo chatear, es integrar una IA potente en tu flujo de trabajo. 💡

#EdTech #IA #Productividad #InnovaciónEducativa #ClaudeAI #TIC

[Virginio Gallardo @virginiog]

Una herramienta subestimada para profesionales: Google AI Studio

Entorno visual diseñado para experimentar directamente con los modelos Gemini: texto, imagen, video

Un laboratorio de prototipos donde puedes definir el comportamiento exacto, las reglas y el contexto de la IA

[Google en español @googleespanol]

Conoce a Gemini 3.5 Live Translate, la nueva IA de Google que traduce voz a voz en tiempo real, manteniendo la entonación y el ritmo natural de la conversación. 🎧🌍

Dile adiós a las respuestas robotizadas y a las pausas incómodas.
¡Y sí, el lanzamiento es global y ya está disponible en LATAM! 🇲🇽🇦🇷🇨🇴

Lo mejor para nuestra región es que el modelo detecta automáticamente más de 70 idiomas y dialectos, adaptándose a la fluidez y a los modismos locales sin tener que configurar nada a mano.

👇

[ollama @ollama]

You can use GLM-5.2 and Kimi-K2.7-Code in Codex with Ollama!

ollama launch codex

ollama launch codex-app

[ClaudeDevs @ClaudeDevs]

Claude Code and Claude Design now sync both ways.

Run /design-sync to pull your design system into your repo and build against your real components, or push what you've built back into Claude Design and keep editing on the canvas.

[ollama @ollama]

open models. ❤️

[WorldofAI @intheworldofai]

DeepSeek GUI just dropped and it’s exactly what power users needed. A clean, local-first desktop agent workspace for DeepSeek with:

• Code Mode - real file ops, planning, reviews, approvals & project context
• Write Mode - excellent Markdown editor with smart AI assistance
• Kun runtime - insane token efficiency (cache-first design, high hit rates)
• IM integration (Feishu/Lark/WeChat) + background scheduled agents

Local, private, cross-platform (macOS/Windows), and already feeling like a polished Codex-style agent environment: https://t.co/uMJyHJ1lts

[santi @santtiagom_]

Si estás empezando con Claude Code, el plugin oficial claude-code-setup te ayuda a entender cómo configurar el entorno para tu proyecto.

Analiza el repo, detecta frameworks y dependencias, y después te recomienda:
> hooks
> skills
> MCPs
> subagents

Te ahorra bastante tiempo entendiendo qué configuraciones y automatizaciones suelen usarse para ese stack.

Para instalarlo:
/plugin install claude-code-setup@claude-plugins-official

[Hernan Zaldivar @vackup]

https://t.co/7IWSzveWoi

[Hernan Zaldivar @vackup]

Debugger Agent for Unit Tests https://t.co/vzzEEJ4cN4 a través de @YouTube

[Hedgie @HedgieMarkets]

🦔Microsoft canceled its internal Claude Code licenses this week after token-based billing made the cost untenable, even for a company with effectively infinite cloud resources. Uber's CTO sent an internal memo warning the company burned through its entire 2026 AI budget in just four months. American AI software prices have jumped 20% to 37%, and GitHub (owned by Microsoft) is dropping flat-rate plans for usage-based billing across its products.

My Take
The AI subsidy era is ending in real time. The same company that put $13 billion into OpenAI and built the Azure infrastructure powering most of Anthropic's compute just looked at the bill from a competitor's coding tool and decided it was not worth paying. That is not a productivity failure on Anthropic's end. Token-based pricing is forcing every enterprise customer to confront the actual cost of running these models at scale, and the number turns out to be far higher than the flat-rate experiments suggested.

This ties directly to my Gemini Flash post yesterday. Anthropic, OpenAI, and Google all raised effective prices in the last six months. Enterprises that built workflows assuming AI costs would keep falling are now watching annual budgets evaporate in months. Two outcomes look likely from here. Either enterprises scale back AI usage to fit budgets, which slows the revenue ramp the labs need to justify their valuations ahead of IPOs, or the labs cut prices and absorb the losses, which makes the unit economics worse at exactly the wrong moment. Both paths land in the same place, the numbers stop working, and somebody has to take the writedown.

Hedgie🤗

[Hernan Zaldivar @vackup]

TypeScript 7 Beta Now Enabled by Default in Visual Studio 2026 18.6 Insiders 3 https://t.co/pA1wBGx0F3

[Nicolás Maggi @nicolasmaggi87]

FINAL

[Hernan Zaldivar @vackup]

DeepSeek V4: características, pruebas de rendimiento y comparativas https://t.co/gH6e8ArvAV #DataCamp vía @DataCamp

[OpenAI @OpenAI]

Introducing GPT-5.5

A new class of intelligence for real work and powering agents, built to understand complex goals, use tools, check its work, and carry more tasks through to completion. It marks a new way of getting computer work done.

Now available in ChatGPT and Codex.

[Hernan Zaldivar @vackup]

SteamOS 3.9 is the closest thing to a perfect desktop Linux I've ever used https://t.co/gbOTwIn1je

[Hernan Zaldivar @vackup]

https://t.co/pqqA8T4w8e

[Nav Toor @heynavtoor]

If I had to become an AI engineer in 90 days, I would not start with courses.

I would build projects from these 10 GitHub repos.

1. LangChain
The LLM application framework on almost every AI engineer JD. If you want to build production LLM apps, start here.
repo → https://t.co/alIh6rDDIu

2. LangGraph
Stateful agents as graphs. The repo JDs mean when they say "agentic workflows."
repo → https://t.co/bzVBn9uecV

3. LlamaIndex
The go-to framework for RAG and document agents. Every "retrieval pipeline" JD points here.
repo → https://t.co/m4oJ9FiCrX

4. CrewAI
Multi-agent teams with roles and tasks. Used in production by enterprises across the Fortune 500.
repo → https://t.co/0xohE065sD

5. Qdrant
A production vector database written in Rust. JDs name it alongside Pinecone, Chroma, and FAISS.
repo → https://t.co/ziSSXW2dzZ

6. Ragas
The standard framework for evaluating RAG pipelines. Hallucination, faithfulness, relevancy, all measurable.
repo → https://t.co/vgOInvREU5

7. Ollama
Run open-source LLMs locally in one command. JDs ask for local inference for cost and privacy reasons.
repo → https://t.co/gyZhUdzsnZ

8. Awesome MCP Servers
Model Context Protocol is the newest skill on JDs. This repo indexes every production MCP server out there.
repo → https://t.co/ejVOgkRJDX

9. Awesome LLM Apps
100+ end-to-end templates for RAG, agents, multi-agent teams, voice agents, and MCP. Real working code.
repo → https://t.co/oXrD5A8K6a

10. AI Agents for Beginners
Microsoft's free 12-lesson curriculum covering the full AI agent stack. No paywall, no signup.
repo → https://t.co/7dNsDw6bTj

AI engineer job descriptions in 2026 keep asking for the same things: RAG, agents, vector databases, evals, MCP.

These 10 repos teach all of it.

Pick one. Build one project. Push it to GitHub. That's how you start.

100% free. 100% open source.

[Hernan Zaldivar @vackup]

I tried Claude Cowork, and I automated myself out of a job https://t.co/zNOCGV2s2w