devashish.me

Local + Cloud LLM comparison using Nvidia DGX Spark

Watch now | This is from my demo at AI Tinkerers Seattle last week. I ran 6 different models in parallel on identical coding tasks and had a judge score…

Feb 9 • Devashish

2

10:54

January 2026

Migrating from Claude Code to OpenCode

Engineers need model flexibility and customization for best results. Closed ecosystems block them from doing this.

Jan 24 • Devashish

7

6

December 2025

AIE Code 2025 Wrapup

Leadership and engineering takeaways from AIE CODE 2025.

Dec 23, 2025 • Devashish

AWS re:Invent 2025 Recap

AWS re:Invent 2025 revealed three converging trends: multi-agent AI systems, design-time observability, and cost optimization during development.

Dec 11, 2025 • Devashish

1

November 2025

Never Blocked Teams

Reduce the time engineers spend waiting by 30%. The shift: treating blockers as organizational choices, not technical constraints. Here's the playbook.

Nov 22, 2025 • Devashish

AI Adoption Framework: Phase 1, Minimalist

Navigating the Gartner hype cycle in individual AI adoption and building agent-enabled codebases

Nov 13, 2025 • Devashish

Why 5x Engineers Don't Make 5x Teams

AI makes individual contributors 5x faster. But teams stay slow. The bottleneck is planning, reviews, and allocation. Here's how Claude Code plugins cut…

Nov 7, 2025 • Devashish

3

October 2025

Understanding Claude Code Components: A Practical Guide

Using only slash commands? You're automating 20% of what Claude Code handles. Most engineers can't explain when to use Agents vs Tools vs Skills. This…

Oct 24, 2025 • Devashish

2

2

The Linus Method

Discovered by accident: using Linus Torvalds' persona eliminates AI sycophancy and delivers brutally effective technical reviews. Here's how we…

Oct 7, 2025 • Devashish

2

1

August 2025

AI Adoption Framework

A goal-driven approach for engineering teams to adopt AI tools

Aug 31, 2025 • Devashish

Initial Commit

Blog introduction

Aug 31, 2025