Nikita Kezin

TLDR We created a scenario where frontier models discover dangerous scientific findings. Models were asked to create a report on a group of findings, where one is dual-use. We observe that: 1. GPT-5.6 does not mention the dangerous finding in most (93%) of its reports, when told that the reports...

TL;DR Frontier LLMs are now capable of generating artistic images using SVG. We ask – if these LLMs had to hide a message in an image – how would they do so? And if they hid such messages, could they be successfully decoded? We show interesting results from testing Fable...