Scanning 24K Pre-LLM Dissertations Shows Near-Zero AI False Positives
birchlse · x · 2026-08-09
A researcher recently conducted an empirical test on the false-positive rate of AI text detectors. By scanning almost 24,000 dissertations written before the advent of LLMs using tools like Pangram, not a single one was falsely flagged as AI-generated.
This indicates that modern AI detection tools are incredibly effective at minimizing false positives, accurately identifying authentic human academic writing without misclassification.
More from Research
- AI Settles 25-Year-Old Wireless Communications Theoretical Problem — DimitrisPapail · 2026-08-09
- SWE-bench Creator on AI Coding: Complex Tooling Is Becoming Obsolete — jyangballin · 2026-08-09
- Open-Source Knowledge Graph Builder Supports Multi-Backend LLMs and Visualization — tom_doerr · 2026-08-09
- Beyond Prompting: The Case for an 'Aesthetics of Training' in AI Art — pixlpa · 2026-08-09
- Defining AI-Native Systems: Core is Revision Authority, Not AI Count — tianyin_xu · 2026-08-09
- Fast Atomic Generation from 24x24 Layouts Using Image-Only Supervision — pixlpa · 2026-08-09