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。
joelsimon.net · 692 words · saved by 1 readers
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
related reading
- Nodal Points Digest #1: Deep Creativity, Cellular Minds and Fiction Machinespoeticengineering.substack.com
- What Is ChatGPT Doing … and Why Does It Work?-Stephen Wolfram Writingswritings.stephenwolfram.com
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
- Using Artificial Intelligence to Augment Human Intelligencedistill.pub
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
- The Unreasonable Effectiveness of Recurrent Neural Networkskarpathy.github.io
- GenAI Handbookgenai-handbook.github.io
- Conversation Designconvodesign101.xyz
- How AI Is Learning to Think in Secretnickandresen.substack.com
- The Unintelligibility is Ours: Notes on Chain of Thought1a3orn.com
- Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activationstransformer-circuits.pub
- Language models can explain neurons in language modelsopenaipublic.blob.core.windows.net