Vector Grounding? – Skywritings

Anon: LLMs are not ungrounded. They are grounded indirectly through the experiences of other people when they speak, the way a blind person’s knowledge of the visual world is mediated by what they re told by (sighted) people. Blind people know a great deal about the visual world — even about color, which can only be directly experienced through vision STEVAN HARNAD: You’re perfectly right that the meanings of words can be grounded indirectly through language (i.e., through more words, whether from dictionaries, encyclopedias, textbooks, articles, lectures, chatting or texting – including texting with ChatGPT, the (sightless) statistical parrot with the immense bellyful of other people’s words, along with the computational means to crunch and integrate those words, partly by a kind of formal verbal figure-completion). Indirect grounding is what gives language (which, by the way, also includes symbolic logic, mathematics and computation as a purely syntactic subset) its immense (possibly

Anon: LLMs are not ungrounded. They are grounded indirectly through the experiences of other people when they speak, the way a blind person’s knowledge of the visual world is mediated by what they re told by (sighted) people. Blind people know a great deal about the visual world — even about color, which can only be directly experienced through vision SH : You’re perfectly right that the meanings of words can be grounded indirectly through language (i.e., through more words, whether from dictionaries, encyclopedias, textbooks, articles, lectures, chatting or texting – including texting w

related reading

• [2304.01481] The Vector Grounding Problemarxiv.org
• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• ChatGPT4 on the cat on the mat – Skywritingsgeneric.wordpress.soton.ac.uk
• Language Models, World Models, and Human Model-Buildinglingo.csail.mit.edu
• The Waluigi Effect (mega-post) — LessWronglesswrong.com
• trees are harlequins, words are harlequins - the voidnostalgebraist.tumblr.com
• Do large language models understand us? | by Blaise Aguera y Arcas | Mediummedium.com
• GenAI Handbookgenai-handbook.github.io
• Against LLM Reductionism — LessWronglesswrong.com
• Andrej Karpathy — AGI is still a decade awaydwarkesh.com
• Large Language Model: world models or surface statistics?thegradient.pub
• The Unintelligibility is Ours: Notes on Chain of Thought1a3orn.com