📜 Restoring ancient text using deep learning: a case study on Greek epigraphy

A project from DeepMind designed to fill in missing text from ancient inscriptions:

Pythia takes a sequence of damaged text as input, and is trained to predict character sequences comprising hypothesised restorations of ancient Greek inscriptions (texts written in the Greek alphabet dating between the seventh century BCE and the fifth century CE). The architecture works at both the character- and word-level, thereby effectively handling long-term context information, and dealing efficiently with incomplete word representations (Figure 2). This makes it applicable to all disciplines dealing with ancient texts (philology, papyrology, codicology) and applies to any language (ancient or modern).

🛰 SpaceX submits paperwork for 30,000 more Starlink satellites

They’ve only launched 60 so far, but it looks like SpaceX has big plans for their future broadband satellite constellation.

🇨🇳 The People’s Republic of China Was Born in Chains

I haven’t read much Chinese history, but its origins and the Mao years were one of the greatest tragedies. And it’s frightening how much of that attitude is still there under the facade:

China today, for any visitor who remembers the country from 20 or 30 years ago, seems hardly recognizable. One of the government’s greatest accomplishments is to have distanced itself so successfully from the Mao era that it seems almost erased. Instead of collective poverty and marching Red Guards, there are skyscrapers, new airports, highways, railway stations, and bullet trains. Yet scratch the glimmering surface and the iron underpinnings of the one-party state become apparent. They have barely changed since 1949, despite all the talk about “reform and opening up.” The legacy of liberation is a country still in chains.