Joel Simon - LLM的道本语，数字领域的“密语”，不受人类语法约束，为“传输效率”而生。

Dimensions of Dialogue. An art/research work by Joel Simon.

2018 A series of small experiments inspired by early proto-writing systems such as cuneiform and hieroglyphs. Here, new writing systems are created by challenging two neural networks to communicate information via images. Using the magic of machine learning, the networks attempt to create their own emergent language isolate that is robust to noise. This is similar to a machine learning architecture called generative adversarial networks (GANs) except that the networks are collaborating and not competing. Above: two entities from Jan Švankmajer's Dimensions of Dialogue that have learned…

saved by

• Yuemin Huang

related reading

• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
• On the Biology of a Large Language Modeltransformer-circuits.pub
• Using Artificial Intelligence to Augment Human Intelligencedistill.pub
• The Unreasonable Effectiveness of Recurrent Neural Networkskarpathy.github.io
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
• Human-like Neural Nets by Catapulting · Gwern.netgwern.net
• Conversation Designconvodesign101.xyz
• The Illustrated Word2vec – Jay Alammar – Visualizing machine learning one concept at a time.jalammar.github.io
• Thousand-dimensional structure — Resolutionresolution.org
• Prism: mapping interpretable concepts and features in a latent space of language | thesephist.comthesephist.com
• [1703.04908] Emergence of Grounded Compositional Language in Multi-Agent Populationsarxiv.org