The AI Engineering Blog
AI coding tools, model comparisons, deployment guides, and the $100 AI Startup Race. Written by developers, for developers.
🤖 Popular AI Guides
How to Run Kimi K3 Locally: The 2.8T Model That Needs a Datacenter
Kimi K3 weights are on HuggingFace (1.56 TB). Here is what hardware you actually need and …
Qwen 3.7 Flash: Alibaba's $0.03/M Vision Model With 1M Context
Qwen 3.7 Flash is a multimodal vision-language model at $0.03/$0.13 per million tokens. 1M…
Claude Opus 5: The to Anthropic's Most Capable Model
Everything about Claude Opus 5: benchmarks, pricing, effort levels, API setup, and how it …
Claude Opus 5 vs Kimi K3: Benchmark Leader vs Open Weights Challenger
Comparing Claude Opus 5 ($5/$25) vs Kimi K3 ($3/$15, 2.8T params). Benchmarks, pricing, op…
AI Dev Weekly #19: Gemini 3.6 Flash Ships, Kimi K3 Goes Open, Poolside Drops 118B
Week of July 17-23: Google ships 3 Gemini models. Kimi K3 is the largest open-weight model…
InclusionAI Ling 3.0 Flash: 124B MoE with Hybrid Reasoning
Ling 3.0 Flash is a 124B MoE model with 5.1B active parameters. Hybrid reasoning mode, 262…
Gemini 3.6 Flash vs Kimi K3: Google's Speed Demon vs China's Largest Model
Gemini 3.6 Flash vs Kimi K3. Price, speed, benchmarks, open weights, and which one to pick…
Gemini 3.5 Flash-Lite: Google's Fastest Model at $0.30 Input
Gemini 3.5 Flash-Lite runs at 350 tok/s and costs $0.30/$2.50 per 1M tokens. Specs, benchm…
📝 Latest Articles
Claude Code vs Aider vs Continue.dev — Terminal AI Coding Tools Compared (2026)
Three terminal-based AI coding tools, three different approaches. Claude Code for autonomy, Aider for git workflows, Con…
System Design Interview: Design an AI Chatbot — Step by Step (2026)
How would you design ChatGPT? A system design walkthrough covering architecture, streaming, conversation memory, RAG, ra…
AI Dev Weekly #20: Claude Opus 5 at Half Fable 5's Price, Flash Models Compared, Image/Video API Pricing
Week of July 24-30: Anthropic ships Opus 5 at $5/$25. Flash model comparison reveals Gemini 3.6 Flash leads. AI image an…
AI Model Evaluation Checklist — 15 Questions Before You Pick a Model (2026)
Before you commit to an AI model for production, ask these 15 questions about quality, cost, latency, privacy, and vendo…
Claude Code Permission Denied Fix: File Access and Git Issues (2026)
Fix 'permission denied' errors in Claude Code. Covers file permissions, git ownership, API key issues, and directory acc…
GPT-5.6 Luna Drops 80% to $0.20/M Input — OpenAI's Response to Claude Opus 5
OpenAI cuts GPT-5.6 Luna to $0.20/$1.20 (80% reduction) and Terra to $2/$12 (20% reduction). Fast mode replaces Priority…