I trained a 113M-parameter earthquake LLM from absolute scratch
What happened
A researcher trained a massive language model called Nanogpt-Seis with 113 million parameters, specifically designed to understand and generate text related to earthquakes. This model is notable because it was built from scratch without using pre-existing models or fine-tuning, demonstrating the potential for self-contained AI development. The model's capabilities could be used to improve earthquake prediction, emergency response, and scientific research.
Why it matters
This achievement showcases the rapid progress in AI model development and the potential for self-contained innovation in the field, which could lead to breakthroughs in various industries and applications.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More from OpenAI
Introducing ChatGPT WalletOpenAI · 13 Nov 2026Shield helps technicians hand off legacy portal work with OpenAIOpenAI · 13 Nov 2026OpenAI launches ChatGPT Wallet, AI agents pay for purchaseOpenAI · 13 Nov 2026OpenAI disbands its robotics team as its general models start running robotsOpenAI · 13 Nov 2026Yang-Mills, OpenAI proof, and the mass gap problemOpenAI · 13 Nov 2026This page was collected from github.com and summarised automatically by AIPulsee's pipeline. See how it runs.