{"type":"link","version":"1.0","title":"Routing environment and human feedback through a frozen LLM as text elicits adaptive behaviors that were never demonstrated in the prompt","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/language-feedback-elicits-untrained-replanning-behaviors","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}