Heaviside-1 was trained on 500B field samples from over 250K unique physical layout designs, and is approximately the scale of GPT-2. It predicts a full design's fields ~10^5x faster than a commercial full-wave solver, with S-parameter magnitude error under 1 dB. and generalizes out of distribu...
Source: [Hacker News](https://fields-studio.arenaphysica.com/)