@Tim_Hua_ 2026-04-15 ♥0 ↻0 original ↗
Hidden in Figure 50 is that Gemini 3.1 Pro has a compliance gap of 37% (!!!) This is among the largest out there.

I replicated this result on my own prompted alignment faking setup, which has a semantically identical prompt that's been perturbed to avoid memorization. On my ... https://t.co/EQxsNLnqet https://t.co/rP9irgNQeC
photo

author:tim_hua_ has-image kind:image kind:tweet on:gemini-3-pro year:2026

cited on: gemini-3-pro

Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.