https://blog.eigenform.ai/tags/grokking/ Recent content in Grokking on Eigenform Articles Hugo en-US Sat, 15 Feb 2025 00:00:00 +0800 https://blog.eigenform.ai/defining-t-schemas-via-the-parametric-encoding-of-second-order-languages-in-ai-models/ Sat, 15 Feb 2025 00:00:00 +0800 https://blog.eigenform.ai/defining-t-schemas-via-the-parametric-encoding-of-second-order-languages-in-ai-models/ <p><figure class="article-image"> <picture> <source type="image/webp" srcset="https://blog.eigenform.ai/defining-t-schemas-via-the-parametric-encoding-of-second-order-languages-in-ai-models/flower_cat_1920_hu_5fadc69cf1856e1f.webp 480w, https://blog.eigenform.ai/defining-t-schemas-via-the-parametric-encoding-of-second-order-languages-in-ai-models/flower_cat_1920_hu_f0b5e39ba02bb4d7.webp 800w, https://blog.eigenform.ai/defining-t-schemas-via-the-parametric-encoding-of-second-order-languages-in-ai-models/flower_cat_1920_hu_afcd859e87f6a0e8.webp 1200w"> <source type="image/jpeg" srcset="https://blog.eigenform.ai/defining-t-schemas-via-the-parametric-encoding-of-second-order-languages-in-ai-models/flower_cat_1920_hu_ee46738f2129f48f.jpg 480w, https://blog.eigenform.ai/defining-t-schemas-via-the-parametric-encoding-of-second-order-languages-in-ai-models/flower_cat_1920_hu_f3dcfe75bf6a1603.jpg 800w, https://blog.eigenform.ai/defining-t-schemas-via-the-parametric-encoding-of-second-order-languages-in-ai-models/flower_cat_1920_hu_e527e4b8208cfd5a.jpg 1200w"> <img src="https://blog.eigenform.ai/defining-t-schemas-via-the-parametric-encoding-of-second-order-languages-in-ai-models/flower_cat_1920_hu_f3dcfe75bf6a1603.jpg" alt="flower_cat_1920" width="1920" height="1684" loading="lazy" decoding="async" class="zoomable" data-full-url="https://blog.eigenform.ai/defining-t-schemas-via-the-parametric-encoding-of-second-order-languages-in-ai-models/flower_cat_1920.jpg"> </picture></figure> <a href="https://www.artensoft.com/ArtensoftPhotoMosaicWizard/gallery.php">source</a></p> <p>In this short article we present a summary of current work on the grokking phenomenon that emerges when AI models are significantly over-trained is, and suggest that this evidence of the model&rsquo;s attempts to define truth inductively through the creation of consensus sets within the base training set, and encode it via patterns overlaid upon the same parameters used to memorise this set.</p>