ChatGPT-6 Astra cracks 217-year-old Napoleonic code in just six hours
TL;DR
An AI engineer used GPT-6 Astra to reveal the contents of a cipher that hadn’t been read since the Napoleonic Wars. The task was initiated with a single image and prompt, and took just six hours from start to finish. An AI engineer used GPT-6 Astra to reveal the contents of a cipher that hadn’t been read since the Napoleonic Wars. The task was initiated with a single image and prompt, and took just six hours from start to finish.
Nauti's Take
Before treating this as a new pattern for historical research, a small team should verify the primary source, the full prompt, and a reproduction with a comparable model. The key checks are error rates, handling of damaged characters, and evidence for each reading, because a plausible decryption can look certain when the source material is incomplete.
Sources