On Susan Li's META Q1 2026 prepared remarks, Claude was the only one of four tools tested to pick up what the CFO did with the word 'underestimate'. She said management had 'previously underestimated' compute needs — language that points upward without making a real commitment. It lets management spend less later if conditions change while still sounding bullish today. ChatGPT, Gemini and Perplexity read the same passage and missed it.
// The Catches
What AI caught.
The counterweight to /lessons. A running index of moments where the model spotted what was missed — a language tell, an asymmetry, a sharper reframe of a thesis. Same evidence bar as the failure log: specific, observable, falsifiable. "AI was helpful" does not qualify; "Claude was the only tool to flag the word 'underestimate' as one-sided phrasing in the META Q1 call" does.
// By tool — 1 entry Claude · 1
// Filter
// Most recent first
No catches match this filter yet.
// The matched pair
Read this alongside /lessons — the failure log. Both pages document the same kind of evidence pointing in different directions.
Every entry is a real moment from a real prompt — no curated highlights, no marketing language. The list grows as new tests turn up new catches. "AI was helpful" does not qualify; the catch has to be specific enough that a sceptical reader could re-run the prompt and check.
The failure log lives at /lessons — same evidence bar, opposite framing. Both pages sit under /evidence — the matched-pair view.
Subscribe to the catch feed: /catches/rss.xml. Combined evidence feed: /evidence/rss.xml.