Guides on writing and editing with AI — every claim tied to a source you can check.
24 posts · page 2 of 3
Fact-Checking AI Output
Yes — a follow-up verify prompt measurably improves citation accuracy (7.5% to 77.5% in one study). No — self-checking still leaves a fifth wrong, because a model can't reliably audit itself.
7 cited sources
AI Detectors
A light paraphrase collapses detector accuracy from 97% to 57% without changing the meaning. That isn't a loophole to exploit — it's proof the score was never evidence.
7 cited sources
AI Detectors
A detector score is not proof of cheating: a 2025 case study scored human writing 0% and the same text, lightly AI-edited, 100%. Here is the policy that follows.
10 cited sources
AI Detectors
Text watermarking is the one AI-detection method that actually works — but it needs control of the model, which the person grading your essay never has.
10 cited sources
Fact-Checking AI Output
A fake citation isn't a botched copy of a real record — the model never had one. It assembles the most probable author, title, and journal, so plausibility is baked in.
5 cited sources
Fact-Checking AI Output
A sourced table of measured AI hallucination rates by model, task, and domain — with the methodology behind each figure kept intact, not averaged away.
9 cited sources
AI Detectors
AI detectors clear human text far better than they catch machine text — and the false positives they do produce land on non-native writers up to 98% of the time.
10 cited sources
Fact-Checking AI Output
A minute is enough to catch a fabricated citation — if you check the fields in the order the errors actually sit. Start with the DOI and PMID, not the title.
8 cited sources
AI Detectors
A detector score is not proof. Here is what to say, what to show, and which peer-reviewed studies to cite when you have to defend work you actually wrote.
9 cited sources