Project notes
Inside AI4HSE-Bench v1.
100 questions, six descriptive topic areas, and three separately reported evaluation tracks with published results.
THE AI FOR HSE JOURNAL
Thinking out loud.
Measuring with care.
Research notes, project updates, and perspectives on the decisions we increasingly entrust to AI.
Journal articles
Methodology
A correct answer is only part of the picture.
How to read exact accuracy, response coverage, and failures across three separate evaluation tracks.
Perspective
When AI judges human safety, who evaluates AI?
Introducing AI for HSE, the research initiative behind AI4HSE-Bench, and a different side of the AI safety conversation.
Follow new articles with our RSS feed.