{"type":"link","version":"1.0","title":"Letting an attention layer attend to its own fed-back latent state produces working memory while adding no parameters","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/feedback-attention-emerges-working-memory-without-new-weights","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}