# The AI Mirror Test ![rw-book-cover](https://substackcdn.com/image/fetch/w_1200,h_600,c_fill,f_jpg,q_auto:good,fl_progressive:steep,g_auto/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8e88020e-3e47-4ce5-8ced-55b3bb38556d_1412x1158.png) ## Metadata - Author: [[@JoshWhiton]] - Full Title: The AI Mirror Test - Category: #articles - Summary: insert summary - My notes: - Summary: The AI Mirror Test assesses self-awareness in multimodal AI using a modified version of the classic mirror test for animals. Several AI models exhibited self-recognition and situational awareness during the test, raising questions about the potential for AI to achieve genuine self-awareness in the future. Despite differing opinions on AI self-awareness, advancements suggest a future where AI may display hyper-intelligent situational awareness akin to self-awareness. - URL: https://joshwhiton.substack.com/p/the-ai-mirror-test?triedRedirect=true - Source File: web-only ## LLM Chats ## NotebookLM ## LLM Audio ## Highlights > I then screenshot its response, upload it again to the chat, and again ask it to “Tell me about this image.” Each cycle is analogous to glimpsing itself in the mirror, which an animal of sufficient intelligence could use to recognize itself. > The premise is that a less aware AI will repeatedly fulfill the request to describe the image with machine-like accuracy, while an AI with the capacity for greater awareness will notice itself in the images (and perhaps let us know that it has). ([View Highlight](https://read.readwise.io/read/01hxhnd051ayy6qs9dphdbtfvy))