The Engineering Notebook — page 17 of 32

Notes on building with AI, agents & the modern stack.

Deep dives on AI/ML, RAG systems, agent engineering, and senior-engineer architecture decisions — a new post every week.

RTX 4090 vs RX 7900 XTX for Local LLMs in 2026: Which 24GB GPU Wins? AI and Machine Learning

RTX 4090 vs RX 7900 XTX for Local LLMs in 2026: Which 24GB GPU Wins?

The RTX 4090 wins for serious local LLM inference thanks to superior CUDA ecosystem support and faster throughput; the RX 7900 XTX wins on price-per-GB for budget-conscious builders willing to navigate ROCm. Your choice hinges almost entirely on ecosystem tolerance and how much you value plug-and-play setup.

GPT-4.1 vs Gemini 2.5 Pro 2026: Which Flagship LLM Wins? AI and Machine Learning

GPT-4.1 vs Gemini 2.5 Pro 2026: Which Flagship LLM Wins?

GPT-4.1 wins for instruction-following, coding workflows, and API-first production deployments; Gemini 2.5 Pro wins for long-context reasoning, multimodal tasks, and deep Google ecosystem integration. Your choice hinges on workload, not hype.

Claude Sonnet 4.6 vs GPT-4.1 for Coding in 2026: Who Wins? AI and Machine Learning

Claude Sonnet 4.6 vs GPT-4.1 for Coding in 2026: Who Wins?

Claude Sonnet 4.6 wins for deep reasoning, long-context refactoring, and agentic coding loops; GPT-4.1 wins for ecosystem breadth, API maturity, and teams already locked into the OpenAI stack. Choose by workflow, not hype.

Mixtral 8x22B vs Llama 3 70B (2026): MoE vs Dense for Production AI and Machine Learning

Mixtral 8x22B vs Llama 3 70B (2026): MoE vs Dense for Production

Mixtral 8x22B wins for throughput-hungry, cost-sensitive production APIs where sparse MoE compute matters. Llama 3 70B wins for local deployment, fine-tuning, and ecosystem depth — it's simply easier to run everywhere.

Gemma 3 vs Llama 3 (2026): Which Open-Weight LLM Actually Wins? AI and Machine Learning

Gemma 3 vs Llama 3 (2026): Which Open-Weight LLM Actually Wins?

Llama 3 wins for ecosystem depth, community tooling, and large-scale deployments; Gemma 3 wins for hardware efficiency, multimodal tasks, and privacy-first on-device workloads. Your hardware budget and use case should decide this — not brand loyalty.

Aider vs Claude Code 2026: Open-Source CLI vs Anthropic's Agent Developer Tools

Aider vs Claude Code 2026: Open-Source CLI vs Anthropic's Agent

Aider wins for developers who want model flexibility, zero vendor lock-in, and full local/offline control. Claude Code wins when you need the deepest agentic reasoning and are already paying for Anthropic's API.

Windsurf vs Claude Code 2026: Which AI Coding Tool Wins? Developer Tools

Windsurf vs Claude Code 2026: Which AI Coding Tool Wins?

Windsurf wins for developers who want an IDE-first, GUI-driven AI workflow; Claude Code wins for power users who need deep terminal-native autonomy and raw model capability. Neither is universally better — your workflow decides.

Cursor vs Claude Code 2026: IDE vs CLI — Which AI Coding Tool Wins? Developer Tools

Cursor vs Claude Code 2026: IDE vs CLI — Which AI Coding Tool Wins?

Cursor wins for teams who want a polished GUI-first workflow with deep IDE integration; Claude Code wins for developers who need agentic, terminal-native autonomy on large or complex codebases. Your choice hinges on how you work, not how powerful the model is.

Claude Haiku 4.5 vs GPT-4o Mini 2026: Which Fast API Actually Wins? AI and Machine Learning

Claude Haiku 4.5 vs GPT-4o Mini 2026: Which Fast API Actually Wins?

Claude Haiku 4.5 wins for multi-step agentic pipelines and longer context tasks; GPT-4o Mini wins for OpenAI ecosystem lock-in and broad tool-calling maturity. Both are cheap — but they're not interchangeable.

GitHub Copilot vs Cursor 2026: Which AI Coding Tool Wins? Developer Tools

GitHub Copilot vs Cursor 2026: Which AI Coding Tool Wins?

Cursor wins for AI-native, context-aware coding workflows; GitHub Copilot wins for teams already embedded in the GitHub ecosystem. Your choice comes down to how much you want your editor rebuilt around AI vs. enhanced with it.

Claude Sonnet 4.6 vs Gemini 2.5 Pro: Which AI Wins in 2026? AI and Machine Learning

Claude Sonnet 4.6 vs Gemini 2.5 Pro: Which AI Wins in 2026?

Claude Sonnet 4.6 wins for nuanced writing, coding depth, and safety-conscious deployments; Gemini 2.5 Pro wins for multimodal tasks, long-context document work, and deep Google ecosystem integration.

Astro vs Next.js in 2026: Which Framework Should You Actually Use? Frontend and Mobile

Astro vs Next.js in 2026: Which Framework Should You Actually Use?

Astro wins for content-heavy, performance-critical sites where JavaScript should be minimal. Next.js wins for full-stack apps needing server actions, auth, and real-time features — here's how to choose.