Asked to review 'Dixon Dixon AI' (a voice-input transcription of dixon.ai), Gemini audited dixonai.com — an unrelated B2B AI…
In a second session naming dixon.ai explicitly, Gemini described my methodology as the 'Filter Method' — an early working name…
Re-ran the BMNR covered-call no-chain test from 2026-05-15 to check if the pattern still reproduces.
I work out how to get reliable answers from AI — and test the methods with real money.
Weekly · what worked, what didn't, the prompts I'd run again.
01 / The Method
The single prompt change that made AI analysis worth using
Start here. The one prompt change that fixes most AI investment outputs.
02 / The Comparison
ChatGPT vs Claude vs Perplexity vs Gemini for stock research (2026): a real test
Which tool to open for which task. Per-task verdicts, no hedging.
03 / The Failure
What AI gets right (and wrong) about options trading
Where AI breaks. Real fabrications, named tools, named failure modes.
Gemini audited my website — and reviewed a different business entirely
I asked Gemini Flash to audit dixon.ai. It audited dixonai.com instead — a B2B consultancy — and wrote a confident report on the wrong company's framework.
Decision ProcessThe AI prompt I run before every sell decision
Every other sell-decision prompt asks AI whether to sell. This one asks AI to audit the thesis you had when you bought — and whether it still holds.
Prompt StackAI earnings call red flags: three phrases that flag almost every time
AI earnings call red flags: three patterns that recur on almost every call. Upward hedges, widening guidance, absent topics. Claude caught all three on META Q1 2026.
// The Method Four prompts that stop AI inventing the answer.
Read →