Receipts
Raw artifacts behind published findings. Prompts, outputs, scoring, and analysis. Open any kit to verify a number or replicate an experiment.
Why 'Don't Be Generic' Doesn't Work
Jul 12, 2026Telling a model 'don't be generic' does nothing on its own; giving it specific anchors does. The gain is verifiability, not quality.
5 files
Three Questions Before You Prompt AI
Jul 5, 2026Three questions before you type structure most of the prompt. Specificity is the strongest single lever (Hedges g=1.34); 'be exceptional' alone does almost nothing.
6 files
Three AIs, No Source, the Same Answer
May 25, 2026Same model, same prompt. The source you paste, not the prompt you write, decides whether the numbers are real.
4 files
AI Amplifies What You Bring
May 6, 2026Same model, same task, two paragraphs of operator context, dramatically different output. The kit, the design history, and the principle for adapting it to your own situation.
4 files
Frame Check
May 5, 2026Drop any document in. See which analytical perspectives it covers, which it skips, the voice, what evidence backs each numerical claim. Free, open source, useful from the first paste.
11 files
Stop Calling It Hallucination
Apr 25, 2026Hallucination is six or more distinct failure modes. Different mechanisms. Different solutions. Name the type first.
4 files
Most AI Numbers Are Unverifiable
Mar 23, 202677 to 100 percent of AI-generated numbers are temporally unstable. Source material fixes it. Prompts don't.
9 files
Why AI Can't Verify Its Own Work
Mar 23, 2026The agent reported clean. The output was wrong. Same process generating and evaluating.
13 files
The Output That Feels Most Trustworthy Is Often the Least Reliable
Mar 23, 2026The signals you use to judge AI trustworthiness are the same signals fabrication produces.
5 files