Juan Suarez

I turned all of this into a 10-slide deck — swipe through. Which insight landed hardest for you? #AI #AgenticAI #FutureOfWork #ArtificialIntelligence #AIAgents #Productivity #SoftwareEngineering #Karpathy

🚀 The takeaway he keeps coming back to: "Everything is a skill issue." The tools are there. The capability is there. The only question is whether you're developing the muscle memory to use them.

You’re not using AI. You’re operating agents. Andrej Karpathy hasn't typed a single line of code since December. Not because he stopped working. Because something fundamentally shifted — and most people still haven't felt it yet.

@TechWith_Nova @AiwithTyler OpenClaw

My OpenClaw bot builds websites & mails a postcard with a QR link to local businesses on autopilot... You can use it to land new customers without a single cold call, here's how it works: - Finds 100s of local businesses via Google Maps - Builds each one a custom website in minutes - Prints a real postcard with their site preview + QR code - Mails it directly to their door - They scan it, see their site, and reach out - Runs 24/7 completely hands off Direct mail gets a much higher response rate than cold email. Reply "OpenClaw" and I'll send you the full breakdown of how you can do it too (must be following so I can DM)

@mattyp Are you sharing the source code?

Browser-native video clipping & captioning tool - Strips audio & transcribes in seconds - Processes video entirely in the browser (no ffmpeg or server upload) - Custom fonts & text overlays - Renders in under a minute Better than 99% of SaaS solutions and practically free - shout out @AssemblyAI & @vanilagy

If the engine is strong enough, you should be able to build real products on top of it. That's the whole point of LTX-2.3. Introducing LTX Desktop. A fully local, open-source video editor running directly on the LTX engine, optimized for NVIDIA GPUs and compatible hardware.

Stage 2 coming: Retrieval & Reranking — follow along. What's your current ingestion stack? Drop it in the comments 👇 #RAG #LLM #AIEngineering #VectorSearch #DocumentAI #MachineLearning #MLOps

📊 Document-aware → tables stay tables, code stays code The bottom line: Ingestion is not setup. Ingestion is architecture. Parse with layout awareness. Chunk semantically. Evaluate with RAGAS before you ship. [ 📎 Slides with full tool comparison matrix attached. ]

Let's talk about Ingestion in RAG pipelines. 🧵 Most teams obsess over which LLM to use. They pick the best embedding model. They tune their prompts to perfection. Then they feed their pipeline garbage documents and wonder why answers are wrong.