GigaChat Creates New Continuation of Gogol's Dead Souls Under Expert Supervision

Sber's GigaChat generative AI model has produced a new version of the second volume of Nikolai Gogol's Dead Souls, which the author himself destroyed in 1852. The project involved training the model on Gogol's writings, letters, drafts, works by his contemporaries, and philosophical and religious texts that may have influenced the writer. Historians, literary scholars, linguists, and engineers guided the process to ensure the creation of original images and meanings rather than recycled phrases. Experts reviewed every fragment of the generated text for authenticity and quality. Illustrations were also produced by an AI model based on the style of Alexander Agin, who illustrated the first volume during Gogol's lifetime. Sber states the goals are to demonstrate AI as a creative and analytical tool in the hands of specialists and to attract younger readers to Russian classics. Vladislav Kreynin noted that the work does not resolve debates about the lost original manuscript.

AntiMalwareTranslated from Russian

Read at source

GigaChat, the generative AI developed by Sber, has generated a continuation of Nikolai Gogol's classic novel Dead Souls under the guidance of historians, literary scholars, linguists, and engineers.

Gogol destroyed the manuscript of the second volume in 1852. The project team created its own version of the further adventures of the character Chichikov. The model was trained on Gogol's complete works, personal letters, surviving drafts, texts by his contemporaries, and philosophical and religious writings that could have inspired the author.

Every generated fragment underwent expert review. The objective was to produce new literary images and meanings instead of reassembling familiar Gogolian phrases. Illustrations for the project were also created by a neural network, drawing stylistic inspiration from the engravings of Alexander Agin, who illustrated the first volume during Gogol's lifetime.

Sber describes the initiative as a literary experiment combining AI with human expertise in both text and visual elements. The two stated goals are to showcase the capabilities of neural networks as tools for analysis and creativity when used by specialists and to engage younger audiences with Russian classical literature.

Vladislav Kreynin emphasized that the project does not settle ongoing scholarly disputes regarding the destroyed original manuscript. Readers are left with a new continuation created jointly by AI and human experts, while the question of what Gogol actually wrote and burned remains unanswered. The effort does, however, provide a genuine reason to revisit the first volume.

Meridian digestThe week's most consequential security stories, distilled into one briefing.See the digest

More in Other

Mail.ru Reduces Lifetime 1TB Cloud Storage Promo to Standard 8GB Quota for Select Users
Kimi K3 Open Model Surpasses Closed AI Leaders with Million-Token Context and 896 Experts
Innostage Completes Functional Testing of PT NGFW 1.10.3 Across 156 Criteria