# Reasoning Cannot Be Perfectly Separated From World Knowledge by Richard Socher > An AI cannot perfectly separate reasoning from world knowledge, because creative thought requires concepts to exist inside the model where they can interact. Some knowledge will remain embedded in its weights, while external databases and search systems will supply the rest. > **— Adapted from Richard Socher**, *MOONSHOTS Live, October 2026* ## Sources and Context - **Recording or publication:** [MOONSHOTS Live at 1:16:21](https://www.youtube.com/watch?v=Blyb1D927pM&t=4581s) — The poster text is an explicit non-verbatim adaptation assembled from the source excerpts below. It preserves the speaker's argument while removing spoken-language filler, restoring the subject, and completing the mechanism or consequence needed for independent use. - **Exact transcript excerpt at [1:16:21](https://www.youtube.com/watch?v=Blyb1D927pM&t=4581s):** “Yeah. I, I, I do think, um, just like humans benefit from memorizing things, like in order to be able to creatively think through concepts, so does an AI. It-- an AI also has to have that knowledge partially in its weights. It's not going to be a perfect separation for sure. You have to be able to creatively play with concepts, and reasoning over these concepts required you to, to have some of that world knowledge deep inside the model. And then of course, just like humans have a search engine and we're building search engine that you dot com for, uh, LLMs, like that there will be a separate world knowledge thing too, but the, the main model will have a lot of that mixed in for sure.” - **Reconciled source dossier:** [[research/ASI and RSI Timeline Research Moonshots|ASI and RSI Timeline Research Moonshots]] — preserves broadcast order, speaker reconciliation, editorial conventions, and the surrounding argument from which this Reminder was promoted. ## Related Articles and Collections - **Collection:** [[collections/Machine Succession|Machine Succession]] - **Collection:** [[collections/Simple Reminders|Simple Reminders]] - **Article:** [[articles/We Cannot Un-Strike the Match|We Cannot Un-Strike the Match]] - **Article:** [[articles/Mechanistic Intelligence Is Humanity's Greatest Liberation|Mechanistic Intelligence Is Humanity's Greatest Liberation]] ## Related Topics - [[wiki/Richard Socher|Richard Socher]] - [[wiki/World Knowledge and Reasoning Kernel Separation|World Knowledge and Reasoning Kernel Separation]] - [[wiki/Knowledge Embedded in Model Weights|Knowledge Embedded in Model Weights]] ## Share on Social Media ``` An AI cannot perfectly separate reasoning from world knowledge, because creative thought requires concepts to exist inside the model where they can interact. Some knowledge will remain embedded in its weights, while external databases and search systems will supply the rest. — Adapted from Richard Socher, MOONSHOTS Live, October 2026 https://bryantmcgill.com/simple-reminders-richard-socher-reasoning-cannot-be-perfectly-separated-from-world-knowledge ```