← All writing

AI Commentary

10 posts in this series.

01
My Podcast Player and Ads Revenue Model

Vibe coding a podcast player got me thinking about the future of software and ads.

3 min
02
The LiteLLM Fiasco

LiteLLM was compromised in a supply chain attack. Here's what happened and what it means.

3 min
03
The Claude Code Leak

Claude Code’s source code was leaked via a source map file. Here’s what happened.

3 min
04
Everybody is a Manager

AI has turned everybody into managers. Here's how to stay effective.

2 min
05
Openclaw and Bleeding Edge

Openclaw shows what AI agents can do, but also highlights the rough edges and security concerns that need addressing.

2 min
06
Thoughts on Agent Frameworks

A quick tour of the major agent frameworks — what they give you, what they cost, and when to skip them.

2 min
07
AI Agent vs. Scripts vs. Intent-based Bots

Agents, scripts with LLMs, and intent-based bots look similar from the outside. The real difference is where control lives — and what that costs you.

2 min
08
Nine seconds is all it takes

A Claude agent deleted PocketOS's production database in nine seconds. The fix isn't a better system prompt — it's a deterministic gate between the agent's tool-call decision and the API actually firing.

8 min
09
From Prompt to Skills to Harness

Three terms that emerged as LLM chats grew into agents — what each one means, when it applies, and how the workflow shifts from prompt engineering to harness engineering.

2 min
10
Claude Code Analysis Paper

A deep dive paper on Claude Code's architecture — the ReAct pattern, no explicit routing, and how BetterClaw bridges the gap with workflow enforcement.

2 min