0812.4360

N/A

# link_2917n7t7hvt.pdf ## Metadata - PDFFormatVersion=1.4 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - Producer=GPL Ghostscript 10.01.2 - CreationDate=D:20241126174204-05'00' - ModDate=D:20241126174204-05'00' - Creator=LaTeX with hyperref package - pdf:producer=GPL Ghostscript 10.01.2 - xmp:modifydate=2024-11-26T17:42:04-05:00 - xmp:createdate=2024-11-26T17:42:04-05:00 - xmp:creatortool=LaTeX with hyperref package ## Contents ### Page 1 arXiv:0812.4360v2 [cs.AI] 15 Apr 2009Driven by Compression Progress: A Simpl

saved by

• Sundus Alfe
• Julian H

related reading

• Formal Theory of Creativity and Fun and Intrinsic Motivation Explains Science, Art, Music, Humor (Juergen Schmidhuber). Artificial Scientists, Artificial Artists, Developmental Robotics, Curiosity, Attention, Surprise, Novelty, Discovery, Opeople.idsia.ch
• 500'000€ Prize for Compressing Human Knowledgeprize.hutter1.net
• Juergen Schmidhuber's home page - Universal Artificial Intelligence - AI - Deep Learning - Recurrent Neural Networks - Computer Vision - Object Detection - Image segmentation - GANs - Transformers with linearized self-attention - Goedel Macpeople.idsia.ch
• Reward is not the optimization target — LessWronglesswrong.com
• Data Compression Explainedmattmahoney.net
• [2309.10668] Language Modeling Is Compressionarxiv.org
• pdfopenreview.net
• Reward Hacking in Reinforcement Learning | Lil'Loglilianweng.github.io
• LLMs can invent their own compression - Rajan Agarwalrajan.sh
• Andrej Karpathy — AGI is still a decade awaydwarkesh.com
• Can gzip be a language model?nathan.rs
• Hutter Prize - Wikipediaen.wikipedia.org