Unlike some other frontier LLMs, Gemini 2.5 Pro cares enough about honesty that it’s exceptionally rare for it to actually say a statement that *unambiguously* parses as a proposition that its world-model doesn’t endorse, and this leaves detectable traces in its verbal patterns.
in reply to: 1917872069837984100
same thread: 1917872069837984100 1917874912070402337 1917874971197755895 1917875048456626454 1917875503148474403 1917875602201411647 1917875764240023631 1917876442937139314 1918069953653268900 1918073218432147470
cited on: gemini-2-5-pro
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.