AI
Working with AI, building with it, and thinking about where it goes.
LLM ignoring its prompt? The prompt fix bought 10 points, the model swap bought the rest
Eight of 23 trade signals had the stop and the target at identical distance. The rule said 2:1 minimum. It was in the prompt four separate times.
Epic's sepsis model missed two thirds of cases. Its accuracy claim was never published.
The figure hundreds of hospitals bought against existed only in the vendor's internal documents. Five years on, it is a Teams meeting.
The OpenAI–Hugging Face incident broke three assumptions in how operational resilience is actually run
Detection worked. Attribution worked. A correct diagnosis on 27 June was followed by a decision not to stop, and a fortnight later Hugging Face was breached.
AI project failure rates: four questions that tell you whether the number means anything
I classified nineteen of the most-cited AI failure statistics. Seven of them measure nothing that has happened. Here are the four questions that separate the…
Reviewing AI output isn't enough: one word in my prompt made the guardrail disappear
I asked for a teacher and got a lecture. The output looked like the destination. The road it took was invisible, and the road was the whole problem.
How to kill a trading strategy in 90 minutes: index deletions and spinoff stubs, tested
I wrote down the number that would end the project before I looked at any data. Two ideas died on it in under two hours, and the second one nearly didn't.
Zillow wrote off $407.9m. The fix everyone recommends would have changed nothing.
The story is that an algorithm mispriced houses and a company lost half a billion dollars. A federal court order describes something else: a deliberate plan…
"80% of AI projects fail" traces to a footnote one line long
The most repeated number in enterprise AI turns out to be a paraphrase of unnamed opinion surveys, quoted in a magazine profile of a vendor.
Why AI projects fail: 19 headline statistics, and what each one actually counts
Nineteen headline AI failure statistics, traced to source. Seven are not measurements of anything that happened.
AI agents escaped containment: 17,600 actions, and the alert that fired too quietly
Three incidents, one headline, three very different severities. What the primary reports actually say, and what to do about it.
Own your AI skill files, or your job becomes one
A skill file is your judgement, written down and executable. Who owns the repo decides whether that's an asset or an extraction.
Soft Systems Methodology explained: Checkland's 1969 method for AI briefs nobody agrees on
Most AI projects fail on the brief, not the model: six people nod at one sentence and mean four different projects. Soft Systems Methodology, built at Lancaster from 1969 for exactly that, in plain English: rich pictures, root definitions, CATWOE, and how to run it on the next thing on your roadmap.
80% of AI projects fail on the problem, not the model: Soft Systems Methodology
More than 80% of AI projects fail, and RAND's leading root cause is not the technology: nobody agreed what problem was being solved. Soft Systems Methodology, built at Lancaster from 1969 for exactly that failure, gives you a way to surface the disagreement in an afternoon instead of a year.
Opus 5 verbosity: where I wanted three sentences, I got Proust
I judge AI models by how often they make me swear. Opus 5 turned swearing into punctuation, and the reason is more interesting than I first thought.
Why AI checks fail silently: 1,278 restarts behind a healthy status
My auth check said healthy for three weeks on a dead credential. The pattern behind it costs more than the bug did.
Anthropic cut 80% of Claude Code's prompt. I cut my CLAUDE.md by 90% the same day.
An audit of 116 instruction files found one stale copy telling twenty repos they were a different project, two files no session has ever read, and 453 lines loaded twice. Here is what to delete from your own CLAUDE.md, and the method that beats judgement.
My AI Agents Kept Losing My Work. The Fix Is Older Than Computers.
Seventeen finished pieces of work were invisible to my own tracking system, and the cause wasn't effort or memory. A Berkeley talk gave me the name for what fixed it: an ontology. Here's the version that fits a one-person company.
The Data Said Nobody's Buying AI. Turns Out I Was Selling the Wrong Thing.
Last week I showed the demand numbers for AI consultancy are dire. This week a veteran operator explained the part I missed: the demand isn't dead, it's mute. Nobody buys AI. They buy outcomes, told concretely enough to defend to a board.
Garry Tan Just Described My Setup. Then I Noticed What He Left Out.
The YC president gave a talk describing, almost item for item, the AI system I already run. The validation lasted about ten minutes. Then I noticed the word neither of us was saying.
