People / Author

Joshua Wendt

Articles by Joshua Wendt on AI implementation, workflow automation, and software engineering.

226 articles · Page 16 of 19

Insight4 min read

GGML and llama.cpp Join Hugging Face: What It Means for Local AI

GGML creator Georgi Gerganov joins Hugging Face to secure the future of local AI inference. A landmark open-source move.

Insight6 min read

Nano Banana 2: What Flash-Speed Image Generation with Web Grounding Actually Means

Google's Nano Banana 2 combines Pro-quality image generation with Flash speed and search grounding. What the architecture implies.

Technical guide32 min read

AI Video: From Diffusion to Directors

How AI video generation works: diffusion foundations, temporal modeling, audio sync, and the multimodal architectures behind Seedance 2.0.

Insight5 min read

OpenAI's Frontier Alliance and GPT-4o Sunset

OpenAI signs multiyear deals with McKinsey, BCG, Accenture, and Capgemini for its Frontier AI agent platform, and retires five older models.

Technical guide29 min read

How AI Benchmarks Actually Work

The benchmarks behind AI model claims: SWE-bench, ARC-AGI-2, GPQA Diamond, and more. What they measure, how they work, and what they miss.

Technical guide23 min read

Agentic AI Architecture Patterns

A guide to agentic AI patterns: ReAct loops, tool-use protocols, multi-step planning, memory, and multi-agent coordination in production.

Technical guide32 min read

Mixture of Experts: Sparse AI Architectures

MoE architectures explained: gating mechanisms, expert routing, load balancing, and why sparse models deliver frontier AI at fraction cost.

Insight5 min read

Gemini 3.1 Pro Leads 12 of 18 Benchmarks

Gemini 3.1 Pro scores 77.1% on ARC-AGI-2, leads on 12 benchmarks, and doubles reasoning power at no price increase.

Insight4 min read

Claude Sonnet 4.6: Near-Opus at 1/5 the Cost

Claude Sonnet 4.6 matches Opus 4.6 on key benchmarks while costing 60% less, reshaping the AI price-performance curve.

Insight5 min read

Alibaba's Qwen 3.5: Multilingual and Open

Qwen 3.5 supports 201 languages, operates autonomously across devices, and ships open-weight under Apache 2.0.

Insight5 min read

MiniMax M2.5: Frontier Coding for Less

Chinese startup MiniMax matches Claude Opus 4.6 on SWE-bench while charging roughly one-tenth the price per token.

Insight6 min read

Seedance 2.0: AI Video Meets Copyright War

Seedance 2.0 debuts at China's Spring Festival Gala, generates Hollywood-quality video from text prompts, and draws a Disney cease-and-desist.