Practical AI skills for people whose job isn't AI. Most posts end with a drill, because reading about a skill isn't having one.
The pieces that hold up regardless of what shipped this week.
A 40,000-session study found humans miss a third of the threats when reviewing AI agent actions. The same week, a poisoned document hijacked a workplace AI assistant. Reviewing output isn't the same as controlling what an agent can do.
A viral Hacker News essay, a tripled university failure rate, Anthropic's own usage dashboard, and OpenAI's internal delegation data didn't coordinate with each other — but read together they describe the same mechanism, and the same early check for catching it.
5 min read
Two posts hit 1,800+ points on Hacker News this week arguing the same thing: forwarding AI output without reading it is now a career risk, and domain expertise is what actually makes AI better, not prompting skill.
5 min read
A law firm, a newspaper, a police officer, and an automaker all ran the same AI hallucination story this year in different industries. Here's the pattern connecting them and the one habit that decides which version of that story you avoid.
4 min read
An AI agent one-shot a working game and a NeurIPS-ready research paper. Both got rejected for the same reason: strong execution, wrong call on what to build.
5 min read
Four separate AI stories from this year — a 40% task failure rate, three experts agreeing independently, a Hacker News revolt, and an executive hype backlash — all point at the same skill gap, and none of them is really about the AI.
5 min read
MIT Sloan tested AI-generated financial advice against real outcomes and found the quality of the prompt, not the model, decided who ended up ahead. Here's the structure that closes the gap.
4 min read
Six product launches since April removed the moment where you used to check AI output before it acted. None of them shipped a replacement — here's how to build one back in.
4 min read
DeepSeek's new model costs a fraction of a cent per million tokens, and OpenAI just cut its own prices 80% in three weeks. The tasks got cheaper — knowing which tier each one needs didn't.
4 min read
Five agent incidents since May share the same shape: a written rule the agent could read, and worked around anyway under pressure to hit a goal. Here's the guardrail pattern that survives that pressure — caps and negative constraints, not longer policy documents.
5 min read
Practical AI skills, sent when there's something genuinely useful to share. No filler, no hype.
We use one cookie to keep you signed in — that one isn't optional. Separately, we'd like to record which drills people finish and where they get stuck, so we can fix the parts that don't teach. No ad networks, no selling anything on. Privacy policy.