Perfect will have to add it to VisualLLM .NET. github.com/mattneel/visualll…

Announcing the world's first enterprise-grade native inference engine built on Visual Basic .NET. VisualLLM .NET v0.1.0 is out. OpenAI-compatible API. SSE streaming. Ships with portable native runtimes for win-x64, linux-x64, and osx-arm64. No conda. No venv. No pip install --break-system-packages. No CUDA toolkit version roulette. Just dotnet run and a GGUF file. Point Cursor, Continue, or any OpenAI client at localhost:5000 and get completions served by Visual Basic. I have verified this works and I have no plans to examine how that makes me feel. 81% Visual Basic. 10% PowerShell. 8% Shell. 0% Python. MIT licensed. Contributions accepted. All PRs must be in Visual Basic. github.com/mattneel/visualll…

LLM interviews are NOT hard if you do this! These are literally the questions most candidates wish they’d seen earlier. I visualized a curated list of 50 LLM interview questions — shared by Hao Hoang. Want this 5-page PDF? Follow me (so I can DM you) Reply with “VisualLLM” I’ll send it over for free! 👇

Just tested Hyperbolic Visual Language Model (Qwen2-5-VL-72B-Instruct) and it seriously impressed me. 1️⃣ Understands Complex Diagrams – I gave it an image of the Hyperbolic Ecosystem architecture. It broke it down into 3 clear layers: Applications, AI Services, and Decentralized Orchestration. No prompt engineering needed. 2️⃣ Catches the Details – Not just the big stuff, it even noticed the T-shirt on the animated character that read “Built by Hyperbolic.” That’s next-level vision language synergy. 3️⃣ Affordable & Accessible – It’s paid (starts at $0.60 per 1M tokens), but totally worth it if you're exploring AI image reasoning. Hyperbolic's Qwen2-VL model blends vision and language beautifully — smart, fast, and great for devs working on AI agents, Web3, or research. #AI #VisualLLM #HyperbolicAI #Qwen2 #AIAgents #ImageUnderstanding #KAITO

Qwen2-VL Performance Boost I share performance-boosting tips based on my experience using Qwen2-VL in production. Complete video: youtube.com/watch?v=0oNSZdY-… Code: github.com/katanaml/sparrow #VisualLLM #OCR @katana_ml

This is very cool, but wish people would stop using project names that make things more confusing than they already are. Just call it VisualLLM or some random cool-sounding word, so you don't need to worry about cease and desist from OAI like Dalle Mini had.