The engineer who built Claude Code dropped a 28-minute video on prompting.
He covers CLAUDE md files for project context, memory shortcuts, parallel sessions, and some useful prompting patterns.
Google's new algorithm just shrunk 31GB of memory down to 4GB 🤯
TurboVec is a new open-source tool that stores the data your AI app searches through, using 16x less memory.
It runs on Google's TurboQuant, which skips the slow setup step every other tool needs.
→ Faster search than the popular alternative (FAISS)
→ Works on both Mac and standard servers
→ Narrow results to exactly what you want
→ Plugs straight into LangChain and LlamaIndex
Your data never leaves your machine. Runs fully offline, works with Python out of the box.
100% Open Source.
Last month we launched Project Glasswing, our collaborative AI cybersecurity initiative. Since then, we and our partners have found more than ten thousand high- or critical-severity vulnerabilities in essential software.
Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors.
Available today at the same price.
You can now use your @grok or X Premium subscription in @opencode.
Use the model powering Grok Build for high speed and codebase intelligence.
https://t.co/8D2F9jYoIQ
🚨Por qué nadie está hablando de ESTO? NVIDIA está regalando acceso GRATIS vía API a más de 80 modelos de IA hosted.
Modelos incluidos:
• MiniMax M2.7
• GLM 5.1
• Kimi 2.5
• DeepSeek 3.2
• GPT-OSS-120B
• Sarvam-M
y muchos más.
Funciona directo con Cursor, Zed, OpenCode, Hermes, OpenClaude, etc.
Cómo configurarlo en 30 segundos:
1. Consigue tu API Key gratis → https://t.co/ayt9aMoZyN
2. Base URL: https://t.co/b2VGhoi3RE
3. Elige el model ID (ej: `minimaxai/minimax-m2.7`)
Si estás prototipando o experimentando con IA esto es inferencia gratis.
La mayoría de builders aún no lo sabe.
Me das las gracias despues.
We just added significantly more NVIDIA Blackwell GPUs to better serve GLM-5.1 model on Ollama's cloud.
We have been adding more GPUs daily for all the other models.
Claude Code:
ollama launch claude --model glm-5.1:cloud
Codex App:
ollama launch codex-app
Hermes Agent:
ollama launch hermes --model glm-5.1:cloud
Run the model:
ollama run glm-5.1:cloud
This is huge!
Turn any codebase into an interactive knowledge graph.
Understand-Anything is a Claude Code plugin that builds an explorable map of your entire project.
Analyzes every file, function, class, and dependency—then gives you an interactive dashboard to explore it all visually.
100% open source.
Here's how 🧵👇
An open-source browser automation engine optimized for scraping, agents, and stealth workflows.
Lower memory usage, instant startup, built-in anti-detection, and full Chrome DevTools Protocol support in a Rust-native stack.
Explore more:
https://t.co/QSJyccJ59s
Tesla Vision allows us to deploy airbags up to 70 milliseconds earlier if your Tesla detects an unavoidable collision
This can be the difference between serious injury & walking away from a crash
FSD V14 is incredibly hyper-aware. The moment the blinker comes on, it recognizes this isn’t just a normal lane change, but a risky move to cut across for the exit. It starts braking in just 0.25 seconds. No human can match that.