Do LLMs Understand?

Understanding, argue Matthieu Queloz and Pierre Beckmann, serves as an efficient proxy for a form of robust competence: it plays a fiduciary role, which is why a conceptual framework of genuine understanding is needed for AI research. Watch the full podcast here:    • Mechanistic Interpretability and How LLMs ...   --------------------------------------- Please consider financially supporting my work (ONLY if you have the means). Patreon: https://patreon.com/trsam?utm_medium=... Substack: https://rsampod.substack.com PayPal: https://paypal.me/rsampod?country.x=A... --------------------------------------- {Podcast} Substack: https://rsampod.substack.com/podcast Spotify: https://open.spotify.com/show/4ryEqju... SFP: https://podcasters.spotify.com/pod/sh... {Website} https://rahulsam.me/ {Social Media} https://substack.com/@trsam/   / name_is_rahul   https://x.com/trsam97   / rahul-samaranayake-981a9315b   --------------------------------------- If the ideas I discuss in this channel evoke your interest, consider visiting https://theunhappyman.substack.com/ --------------------------------------- Copyright Disclaimer under section 107 of the Copyright Act 1976, allowance is made for “fair use” for purposes such as criticism, comment, news reporting, teaching, scholarship, education and research. Fair use is a use permitted by copyright statutes that might otherwise be infringing. If you are or represent the copyright owner of materials used in this video and have a problem with the use of the related material, please email me at [email protected], and we can sort it out. Thank you.