My AI Adoption Journey – Mitchell Hashimoto

kept by eddie feb 06

Mitchell Hashimoto details his phased AI adoption journey, finding efficiency by moving from chatbots to agents, outsourcing reliable tasks, and engineering harnesses to prevent errors.

One Week of Building and Reviewing Code With LLM Agents
Logging a week of agent‑driven backend work, the engineer shows LLMs generated most code, isolated agents found real bugs, while multi‑tool agreement often missed defects.
also on Amp, Claude Code, #ai-coding, #software-engineering, #productivity, #developer-tools
When does MCP make sense vs CLI?
The Hacker News discussion weighs the trade-offs between MCP and CLI for AI agent tool calling, finding that each has valid use cases depending on context.
also on Amp, Claude Code, #ai-agents, #software-engineering, #developer-tools
GitHub - mitchellh/vouch: A community trust management system based on explicit vouches to participate.
Vouch is a trust management system requiring users to be vouched for before contributing, designed to filter low-quality AI-generated contributions in open-source projects.
also on Mitchell Hashimoto, Ghostty, #developer-tools
Autoresearch, Claude and Constrained Optimization
An experiment using Claude Code to autonomously optimize a file compression algorithm over 10 iterations, achieving competitive results against standard tools by iterating on an LZSS-based approach.
also on Mitchell Hashimoto, Claude Code, #ai-coding, #software-engineering, #developer-tools
Coding Agents in Feb 2026
The author compares coding agents Claude Code and Codex, favoring Opus for planning and Codex for fewer bugs, and automates workflows with skills.
also on Ghostty, Claude Code, #ai-coding, #software-engineering, #productivity, #developer-tools