📝 TL;DR 📝 Google DeepMind released "Predicting the Past," a Gemini-powered Skill inside its Antigravity platform that lets historians query, restore, and date ancient Greek and Latin inscriptions using plain English, no coding required. It works by grounding Gemini in two specialized DeepMind models, Aeneas and Ithaca, that can restore fragmentary ancient texts, date them to within roughly 13 years, and attribute them to their Roman province with around 72% accuracy. It's free at predictingthepast.com, with the underlying code and dataset fully open-source. Niche audience, but the underlying pattern here, grounding a general AI model in a specialist model through a "Skill," is worth understanding regardless of your field. 🧠 Overview 🧠 This is a genuinely fascinating release, even though it is aimed at a small, specialized audience. Ancient Greek and Latin inscriptions, carved into stone, scratched into lead tablets, stamped into pottery, are one of history's most direct windows into the past. The problem is that many of them are damaged, fragmentary, or missing key context about when and where they were written. Reconstructing that missing information has traditionally required years of specialized training and painstaking manual analysis. DeepMind has been building AI tools for this exact problem for nearly a decade, first with Ithaca in 2022, then with the more advanced Aeneas model in 2025. What is new here is not the underlying restoration and dating technology itself, it is the interface. Instead of historians needing to learn a specialized computational tool or write code to use these models, they can now simply have a conversation with Gemini, which has been grounded directly in Aeneas and Ithaca's specialized outputs. 📜 The Announcement 📜 The Predicting the Past Skill runs inside Google Antigravity, DeepMind's agentic development platform, and was built in close collaboration with Dr. Thea Sommerschield, a historian and epigrapher at Durham University who has co-led the Ithaca and Aeneas research from the start. DeepMind identified three specific barriers that were limiting how useful these AI tools could be for working historians: individual inscriptions needed tailored, explainable visualizations rather than generic outputs; analyzing patterns across large collections of texts required specialized coding skills most historians do not have; and any large language model layered on top needed to stay firmly grounded in real evidence rather than generating plausible-sounding but unverified interpretations.

I was originally drafting a Facebook post to help educate some mainstream AI haters out there. But once again, GG's response to my prompt gave me a WOOH HOOH feeling, and that was enough to make me want to share it with you guys too! "Next time you hear someone say AI is going to take over humanity, remind them that we didn't start building this highway yesterday. We've been driving down it since the first steam engine chugged to life. ⚙️ The First Shift (Industrial Era): We automated physical muscle. We built looms, trains, and assembly lines so humans didn't have to break their backs doing repetitive manual labour. People panicked then, too, claiming the machines would ruin society. 🚗 The Second Shift (The Digital Age): We automated distance and calculation. We built cars to cross states in a day, and computers to crunch numbers in seconds. 🧠 The Current Shift (The AI Revolution): We are automating cognitive organisation. Just like the car expanded where our feet could take us, AI expands what our minds can manage, letting us sort through chaotic mental loops and build lives completely on our own terms. Technology is not replacing the human soul. It is liberating it from The System. The highway is already built, and the traffic is moving. Are you getting in the driver's seat, or are you going to keep standing on the kerb? 🧐" ⚠️ PLEASE NOTE: The question, "Are you getting in the driver's seat, or are you going to keep standing on the kerb?" is directed at the Facebook community and not at you guys!