- See Also
-
Gwern
- “Movie Reviews”, Gwern 2014
- “Anime Reviews”, Gwern 2010
- “Utext: Rich Unicode Documents”, Gwern 2023
- “Miscellaneous”, Gwern 2009
- “Novelty Nets: Classifier Anti-Guidance”, Gwern 2024
- “InvertOrNot.com Proposal”, Gwern 2021
- “The Second Apocalypse: Freedom In An Unfree Universe”, Gwern 2017
- “Review Of The Quantum Thief Trilogy”, Gwern 2022
- “Interpreting ‘Suzanne Delage’ As Dracula”, Gwern 2009
- “Research Ideas”, Gwern 2017
-
Links
- “Observation Learning in Cats”, John et al 1968
- “Interleaved Practice Improves Mathematics Learning”, Rohrer et al 2014b
- “The Dimpled Manifold Model of Adversarial Examples in Machine Learning”, Shamir et al 2021
- “Fixed Point Diffusion Models”, Bai & Melas-Kyriazi 2024
- “A Tale of Two Sieves”, Pomerance 1996
- “Improvement in Memory Span”, Martin & Fernberger 1929
- “School Closures during the 1918 Flu Pandemic”, Ager et al 2024
- “Relationship Quality and Stability in Couples When One Partner Suffers From Borderline Personality Disorder”, Bouchard et al 2009
- “Hearing Water Temperature: Characterizing the Development of Nuanced Perception of Sound Sources”, Agrawal & Schachner 2022
- “Olfactory Training Is Helpful in Postinfectious Olfactory Loss: A Randomized, Controlled, Multicenter Study”, Damm et al 2013
- “Robustness May Be at Odds With Accuracy”, Tsipras et al 2018
- “Adversarial Robustness As a Prior for Learned Representations”, Engstrom et al 2019
- “Human-Producible Adversarial Examples”, Khachaturov et al 2023
- “Scaling the Scattering Transform: Deep Hybrid Networks”, Oyallon et al 2017
- “Mimetic Initialization of Self-Attention Layers”, Trockman & Kolter 2023
- “Using Counterfactual Tasks to Evaluate the Generality of Analogical Reasoning in Large Language Models”, Lewis & Mitchell 2024
- “Robust Agents Learn Causal World Models”, Richens & Everitt 2024
- “Zero-Shot Tokenizer Transfer”, Minixhofer et al 2024
- “Equal Numbers of Neuronal and Nonneuronal Cells Make the Human Brain an Isometrically Scaled-Up Primate Brain”, Azevedo et al 2009
- “An Exceptional Talent For Calculative Thinking”, Hunter 1962
- “NBC-Softmax: Darkweb Author Fingerprinting and Migration Tracking”, Kulatilleke et al 2022
- “Signing Party: The Artists Sign Their Work”, Hertzfeld 2004
- “Stockfish and Lc0, Test at Different Number of Nodes”, Meloni 2021
- “Electric Fields Elicit Ballooning in Spiders”, Morley & Robert 2018
- “Tempo and Pattern of Avian Brain Size Evolution”, Ksepka et al 2020
- “Meet MAI-1: Microsoft Readies New AI Model to Compete With Google, OpenAI”, Holmes 2024
- “Genetic Influences on Depression and Selection into Adverse Life Experiences”, Rauf & Freese 2024
- “Big Birds and Their Brains: Paleoneurology of the New Zealand Moa”, Ashwell & Scofield 2007
- “Thoughts on OpenAI [redacted]”, Scott & Nadella 2019b
- “Solar Eclipses and the Origins of Critical Thinking and Complexity”, Litina & Fernández 2023
- “Heresy, Witchcraft, Jean Gerson, Scepticism and the Use of Placebo Controls”, Kirakosian et al 2023
- “Ballooning Spiders: The Case for Electrostatic Flight”, Gorham 2013
- “Gradient Diversity: a Key Ingredient for Scalable Distributed Learning”, Yin et al 2017
- “Learning and Evaluating General Linguistic Intelligence”, Yogatama et al 2019
- “What BERT Is Not: Lessons from a New Suite of Psycholinguistic Diagnostics for Language Models”, Ettinger 2019
- “Can Neural Networks Acquire a Structural Bias from Raw Linguistic Data?”, Warstadt & Bowman 2020
- “A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP”, Zhao et al 2021
- “A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision”, Beyer et al 2023
- “Infini-Gram: Scaling Unbounded n-Gram Language Models to a Trillion Tokens”, Liu et al 2024
- “SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-Trained Models”, Deng et al 2024
- “Evaluating Subword Tokenization: Alien Subword Composition and OOV Generalization Challenge”, Batsuren et al 2024
- “ImageInWords: Unlocking Hyper-Detailed Image Descriptions”, Garg et al 2024
- “Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers”, Gu et al 2024
- “A Rotation and a Translation Suffice: Fooling CNNs With Simple Transformations”, Engstrom et al 2024
- “Long-Range Subjective-Probability Forecasts of Slow-Motion Variables in World Politics: Exploring Limits on Expert Judgment”, Tetlock et al 2023
- “OpenAI Quietly Deletes Ban on Using ChatGPT for ‘Military and Warfare’: The Pentagon Has Its Eye on the Leading AI Company, Which This Week Softened Its Ban on Military Use”, Biddle 2024
- “Leaked Deck Reveals How OpenAI Is Pitching Publisher Partnerships: OpenAI's Preferred Publisher Program Offers Media Companies Licensing Deals”, Stenberg 2024
- “Pattern Separation in the Hippocampus”, Yassa & Stark 2011
- “Assessment of Vibration of Effects due to Model Specification Can Demonstrate the Instability of Observational Associations”, Patel et al 2015
- “Man Who Inspired Rain Man Dies At 58”, Berkes 2009
- “The Persistence and Transience of Memory”, Richards & Frankland 2017
- “Are Bigger Brains Better?”, Chittka & Niven 2009
- “Targeting the GIPR for Obesity: To Agonize or Antagonize? Potential Mechanisms”, Ampbell 2012
- Wikipedia
- Miscellaneous
- Link Bibliography
See Also
Gwern
“Movie Reviews”, Gwern 2014
“Anime Reviews”, Gwern 2010
“Utext: Rich Unicode Documents”, Gwern 2023
“Miscellaneous”, Gwern 2009
“Novelty Nets: Classifier Anti-Guidance”, Gwern 2024
“InvertOrNot.com Proposal”, Gwern 2021
“The Second Apocalypse: Freedom In An Unfree Universe”, Gwern 2017
“Review Of The Quantum Thief Trilogy”, Gwern 2022
“Interpreting ‘Suzanne Delage’ As Dracula”, Gwern 2009
“Research Ideas”, Gwern 2017
Links
“Observation Learning in Cats”, John et al 1968
“Interleaved Practice Improves Mathematics Learning”, Rohrer et al 2014b
“The Dimpled Manifold Model of Adversarial Examples in Machine Learning”, Shamir et al 2021
The Dimpled Manifold Model of Adversarial Examples in Machine Learning
“Fixed Point Diffusion Models”, Bai & Melas-Kyriazi 2024
“A Tale of Two Sieves”, Pomerance 1996
View PDF:
“Improvement in Memory Span”, Martin & Fernberger 1929
View PDF:
“School Closures during the 1918 Flu Pandemic”, Ager et al 2024
“Relationship Quality and Stability in Couples When One Partner Suffers From Borderline Personality Disorder”, Bouchard et al 2009
“Hearing Water Temperature: Characterizing the Development of Nuanced Perception of Sound Sources”, Agrawal & Schachner 2022
Hearing water temperature: Characterizing the development of nuanced perception of sound sources
“Olfactory Training Is Helpful in Postinfectious Olfactory Loss: A Randomized, Controlled, Multicenter Study”, Damm et al 2013
“Robustness May Be at Odds With Accuracy”, Tsipras et al 2018
“Adversarial Robustness As a Prior for Learned Representations”, Engstrom et al 2019
Adversarial Robustness as a Prior for Learned Representations
“Human-Producible Adversarial Examples”, Khachaturov et al 2023
“Scaling the Scattering Transform: Deep Hybrid Networks”, Oyallon et al 2017
“Mimetic Initialization of Self-Attention Layers”, Trockman & Kolter 2023
“Using Counterfactual Tasks to Evaluate the Generality of Analogical Reasoning in Large Language Models”, Lewis & Mitchell 2024
“Robust Agents Learn Causal World Models”, Richens & Everitt 2024
“Zero-Shot Tokenizer Transfer”, Minixhofer et al 2024
“Equal Numbers of Neuronal and Nonneuronal Cells Make the Human Brain an Isometrically Scaled-Up Primate Brain”, Azevedo et al 2009
“An Exceptional Talent For Calculative Thinking”, Hunter 1962
“NBC-Softmax: Darkweb Author Fingerprinting and Migration Tracking”, Kulatilleke et al 2022
NBC-Softmax: Darkweb Author fingerprinting and migration tracking
“Signing Party: The Artists Sign Their Work”, Hertzfeld 2004
“Stockfish and Lc0, Test at Different Number of Nodes”, Meloni 2021
“Electric Fields Elicit Ballooning in Spiders”, Morley & Robert 2018
“Tempo and Pattern of Avian Brain Size Evolution”, Ksepka et al 2020
“Meet MAI-1: Microsoft Readies New AI Model to Compete With Google, OpenAI”, Holmes 2024
Meet MAI-1: Microsoft Readies New AI Model to Compete With Google, OpenAI
“Genetic Influences on Depression and Selection into Adverse Life Experiences”, Rauf & Freese 2024
Genetic influences on depression and selection into adverse life experiences
“Big Birds and Their Brains: Paleoneurology of the New Zealand Moa”, Ashwell & Scofield 2007
Big Birds and Their Brains: Paleoneurology of the New Zealand Moa
“Thoughts on OpenAI [redacted]”, Scott & Nadella 2019b
“Solar Eclipses and the Origins of Critical Thinking and Complexity”, Litina & Fernández 2023
Solar Eclipses and the Origins of Critical Thinking and Complexity
“Heresy, Witchcraft, Jean Gerson, Scepticism and the Use of Placebo Controls”, Kirakosian et al 2023
Heresy, witchcraft, Jean Gerson, scepticism and the use of placebo controls
“Ballooning Spiders: The Case for Electrostatic Flight”, Gorham 2013
“Gradient Diversity: a Key Ingredient for Scalable Distributed Learning”, Yin et al 2017
Gradient Diversity: a Key Ingredient for Scalable Distributed Learning
“Learning and Evaluating General Linguistic Intelligence”, Yogatama et al 2019
“What BERT Is Not: Lessons from a New Suite of Psycholinguistic Diagnostics for Language Models”, Ettinger 2019
What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models
“Can Neural Networks Acquire a Structural Bias from Raw Linguistic Data?”, Warstadt & Bowman 2020
Can neural networks acquire a structural bias from raw linguistic data?
“A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP”, Zhao et al 2021
A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP
“A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision”, Beyer et al 2023
A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision
“Infini-Gram: Scaling Unbounded n-Gram Language Models to a Trillion Tokens”, Liu et al 2024
Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens
“SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-Trained Models”, Deng et al 2024
SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Models
“Evaluating Subword Tokenization: Alien Subword Composition and OOV Generalization Challenge”, Batsuren et al 2024
Evaluating Subword Tokenization: Alien Subword Composition and OOV Generalization Challenge
“ImageInWords: Unlocking Hyper-Detailed Image Descriptions”, Garg et al 2024
“Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers”, Gu et al 2024
“A Rotation and a Translation Suffice: Fooling CNNs With Simple Transformations”, Engstrom et al 2024
A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations
“Long-Range Subjective-Probability Forecasts of Slow-Motion Variables in World Politics: Exploring Limits on Expert Judgment”, Tetlock et al 2023
“OpenAI Quietly Deletes Ban on Using ChatGPT for ‘Military and Warfare’: The Pentagon Has Its Eye on the Leading AI Company, Which This Week Softened Its Ban on Military Use”, Biddle 2024
“Leaked Deck Reveals How OpenAI Is Pitching Publisher Partnerships: OpenAI's Preferred Publisher Program Offers Media Companies Licensing Deals”, Stenberg 2024
“Pattern Separation in the Hippocampus”, Yassa & Stark 2011
“Assessment of Vibration of Effects due to Model Specification Can Demonstrate the Instability of Observational Associations”, Patel et al 2015
“Man Who Inspired Rain Man Dies At 58”, Berkes 2009
“The Persistence and Transience of Memory”, Richards & Frankland 2017
“Are Bigger Brains Better?”, Chittka & Niven 2009
“Targeting the GIPR for Obesity: To Agonize or Antagonize? Potential Mechanisms”, Ampbell 2012
Targeting the GIPR for obesity: To agonize or antagonize? Potential mechanisms
Wikipedia
Miscellaneous
-
/doc/ai/nn/transformer/attention/2023-trockman-figure7-gpt2attentionmatrixpatterns.png
: -
/doc/psychology/animal/bird/neuroscience/2020-ksepka-figure2-birdbrainscalingcurves.jpg
: -
/doc/science/2018-morley-video-electricalspiderballooning-1-s2.0-S0960982218306936-mmc2.mp4
: -
/doc/science/2018-morley-videoabstract-electricalspiderballoon-1-s2.0-S0960982218306936-mmc4.mp4
: -
https://twitter.com/VictorTaelin/status/1790183986096116189
: -
https://cabel.com/2024/05/16/the-forged-apple-employee-badge/
-
https://commons.wikimedia.org/wiki/File:SUN_microsystems_logo_ambigram.png
: -
https://distill.pub/2019/advex-bugs-discussion/original-authors/
:View External Link:
https://distill.pub/2019/advex-bugs-discussion/original-authors/
-
https://github.com/kagisearch/llm-chess-puzzles?tab=readme-ov-file#results
-
https://www.atlasobscura.com/articles/agar-art-dangers-of-bacteria-art
-
https://www.chinatalk.media/p/where-does-china-stand-in-the-ai
-
https://www.fujitsu.com/global/about/resources/news/press-releases/2024/0510-01.html
-
https://www.hnn.us/article/frank-ramsey-a-genius-by-all-tests-for-genius
-
https://www.lesswrong.com/posts/pEZoTSCxHY3mfPbHu/catastrophic-goodhart-in-rl-with-kl-penalty
-
https://www.thepsmiths.com/p/review-the-spirit-of-the-mountains
Link Bibliography
-
https://arxiv.org/abs/2401.08741
: “Fixed Point Diffusion Models”, -
https://arxiv.org/abs/1703.08961
: “Scaling the Scattering Transform: Deep Hybrid Networks”, -
https://arxiv.org/abs/2305.09828
: “Mimetic Initialization of Self-Attention Layers”, -
https://www.sciencedirect.com/science/article/pii/S0960982218306936
: “Electric Fields Elicit Ballooning in Spiders”, -
2023-litina.pdf
: “Solar Eclipses and the Origins of Critical Thinking and Complexity”, -
2023-kirakosian.pdf
: “Heresy, Witchcraft, Jean Gerson, Scepticism and the Use of Placebo Controls”, -
https://arxiv.org/abs/2108.13002#microsoft
: “A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP”, -
https://arxiv.org/abs/2404.13292
: “Evaluating Subword Tokenization: Alien Subword Composition and OOV Generalization Challenge”, -
https://arxiv.org/abs/2405.02793#google
: “ImageInWords: Unlocking Hyper-Detailed Image Descriptions”, -
https://theintercept.com/2024/01/12/open-ai-military-ban-chatgpt/
: “OpenAI Quietly Deletes Ban on Using ChatGPT for ‘Military and Warfare’: The Pentagon Has Its Eye on the Leading AI Company, Which This Week Softened Its Ban on Military Use”, -
https://www.npr.org/2009/12/22/121774906/man-who-inspired-rain-man-dies-at-58
: “Man Who Inspired Rain Man Dies At 58”, -
https://www.sciencedirect.com/science/article/pii/S0896627317303653
: “The Persistence and Transience of Memory”,