- cross-posted to:
- [email protected]
- cross-posted to:
- [email protected]
For one month beginning on October 5, I ran an experiment: Every day, I asked ChatGPT 5 (more precisely, its “Extended Thinking” version) to find an error in “Today’s featured article”. In 28 of these 31 featured articles (90%), ChatGPT identified what I considered a valid error, often several. I have so far corrected 35 such errors.
The first edit was undoing a vandalism that persisted for 5 years. Someone changed the number of floors a building had from 67, to 70.
A friendly reminder to only use Wikipedia as a summary/reference aggregate for serious research.
This is a cool tool for checking these sorts of things, run everything through the LLM to flag errors and go after them like a wack-a-mole game instead of a hidden object game.