Study: AI grades essays higher than humans, unreliable
A study in Assessment & Evaluation in Higher Education found ChatGPT graded 50 undergraduate bioscience essays higher than humans in all but one case, with one AI-human gap of 40 points. AI inflated low-scoring essays and deflated high-scoring ones, showing poor alignment with human marks.
How this story unfolded
6 days · 1 report · 2 community posts · from Aug 21
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Plaud unveils 4G-connected AI earbuds for on-the-go tasks
- Adobe adds AI Assisted Editor interface to Photoshop
- Webinar: Build AI threat readiness for security ops
- Anthropic's Mike Krieger: Claude ported 100k lines of Python to TypeScript in a weekend
- OpenAI to show ads on ChatGPT free and Go tiers in India