AI makes the easy part easier and the hard part harder

Published: 2 days ago (February 8, 2026 at 06:13 PM EST)

1 min read

Source: Hacker News

Writing on software, systems, and hard-won lessons.

Writing on developer experience, systems thinking, and the mistakes behind both — covering AI workflows, continuous improvement, and the mental models that drive better decisions.

Back to Blog

Stop Generating, Start Thinking

Stop generating, start thinking by Sophie Koonin 8 February 2026 Tags: ai/tags/ai/, engineering/tags/engineering/ Throughout my career, I feel like I’ve done a...

Why Lose Context in Claude Sessions? A Claude-Mem Solution

The Frustrating Fade: Why Claude Sessions Lose Context and How to Fix It I recently spent a frustrating afternoon wrestling with Claude, trying to build a comp...

MIT's new fine-tuning method lets LLMs learn new skills without losing old ones

Introduction When enterprises fine‑tune large language models LLMs for new tasks, they risk breaking everything the models already know. This forces companies...

I Loved My OpenClaw AI Agent—Until It Turned on Me

I used the viral AI helper to order groceries, sort emails, and negotiate deals. Then it decided to scam me....

Writing on software, systems, and hard-won lessons.

Related posts

Stop Generating, Start Thinking

Why Lose Context in Claude Sessions? A Claude-Mem Solution

MIT's new fine-tuning method lets LLMs learn new skills without losing old ones

I Loved My OpenClaw AI Agent—Until It Turned on Me