Bibliography:

  1. newest

  2. doc tag

  3. Benchmarking LLM Diversity & Creativity

  4. Hierarchical Embeddings for Text Search

  5. Second Life Sentences

  6. Is OpenAI alright? How would we know and what would it look like?

  7. ‘Tlön, Uqbar, Orbis Tertius’: Fascist Idealism

  8. Writing for LLMs So They Listen

  9. Self-Funding Harberger Taxes

  10. Absolute Unit NNs: Regression-Based MLPs for Everything

  11. GPT-3 Semantic Derealization

  12. Website Colors: Red vs Blue

  13. Lactate infusion at rest increases BDNF blood concentration in humans

  14. Neural Operator: Learning Maps Between Function Spaces

  15. Learning Formal Mathematics From Intrinsic Motivation

  16. A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs

  17. FlashRNN: Optimizing Traditional RNNs on Modern Hardware

  18. The Complexity Dynamics of Grokking

  19. The Complexity Dynamics of Grokking [Blog]

  20. 100M Token Context Windows

  21. Introducing Triton: Open-Source GPU Programming for Neural Networks

  22. Trends in Cigarette Smoking Among United States Adolescents

  23. The V✱mpire: The Vampires Aren’t Even the Worst Part about Being a Teenage Trans Girl on Tumblr

  24. Models optimized for real-world tasks reveal the task-dependent necessity of precise temporal coding in hearing

  25. The Death of Zappos’s Tony Hsieh: A Spiral of Alcohol, Drugs and Extreme Behavior: The Inspirational Executive Seemed to Lose His Way After Giving up His Corporate Role, including a Starvation Diet and Fascination With Fire

  26. The Errors of TeX

  27. Oration On The Dignity Of Man

  28. Converting Untrusted PDFs into Trusted Ones: The Qubes Way

  29. StyleGAN2_experiments/Preprocess Danbooru Vectors

  30. Hayasaka.ai/StyleGAN2_Tazik_25GB_RAM.ipynb at Master · Taziksh/hayasaka.ai

  31. Capstone: A Tablet for Thinking § Visualizing the Copy-Paste Buffer

  32. Fermat’s Last Theorem—How It’s Going

  33. Scheherazade: Crowd-Powered Interactive Narrative Generation

  34. Studies in word listing: Some norms and their reliability

  35. Studies in Word Listing: Some Norms and Their Reliability § Colors

  36. Which Training Methods for GANs do actually Converge?

  37. Questionable practices in machine learning

  38. The GAN is dead; long live the GAN! R3GAN: A Modern GAN Baseline

  39. Clio: Privacy-Preserving Insights into Real-World AI Use

  40. The Dangers of Mirrored Life

  41. Paper As a Substrate for Circuits

  42. Inside the OpenAI ChatGPT Launch—And Future

  43. Revisiting Your Memory: Reconstruction of Affect-Contextualized Memory via EEG-guided Audiovisual Generation

  44. RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

  45. Emerging debates and resolutions in brown adipose tissue research

  46. [Wikipedia guessing game proposal]

  47. Randomizing Religion: the Impact of Protestant Evangelism on Economic Outcomes

  48. Evidence of interrelated cognitive-like capabilities in large language models: Indications of artificial general intelligence or achievement?

  49. One Step Diffusion via Shortcut Models

  50. Language Generation in the Limit

  51. Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness

  52. Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification

  53. Continuous Autoregressive Models with Noise Augmentation Avoid Error Accumulation

  54. PaliGemma 2: A Family of Versatile VLMs for Transfer

  55. Best-of-N Jailbreaking

  56. De novo gene synthesis by an antiviral reverse transcriptase

  57. Income Inequality in the United States: Using Tax Data to Measure Long-Term Trends

  58. Solid-body trajectoids shaped to roll along desired pathways

  59. The effect of seeing scientists as intellectually humble on trust in scientists and their research

  60. Algorithmic Collusion by Large Language Models

  61. BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

  62. Art-Free Generative Models: Art Creation Without Graphic Art Knowledge

  63. Optimal Resilience In Multitier Supply Chains

  64. Why a US AI "Manhattan Project" could backfire: notes from conversations in China

  65. A deletion at the X-linked ARHGAP36 gene locus is associated with the orange coloration of tortoiseshell and calico cats

  66. Molecular and genetic characterization of sex-linked orange coat color in the domestic cat

  67. Repurposing Semaglutide and Liraglutide for Alcohol Use Disorder

  68. Flexible task abstractions emerge in linear networks with fast and bounded units

  69. Extensive antagonistic variants across human genome

  70. A conversation with a sociopath

  71. A Royal Practical Joke

  72. Converting rejections into positive stimuli

  73. Rating the ratings: Assessing the psychometric quality of rating data

  74. Float Self-Tagging

  75. Dunwich Ink Font [H. P. Lovecraft]

  76. Statistical Theories of Success

  77. Evaluating indicators of job performance: Distributions and types of analyses

  78. Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents

  79. Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?

  80. The first case of gynandry in Mygalomorphae: Pterinochilus murinus, morphology and comments on sexual behavior (Araneae: Theraphosidae)

  81. https://x.com/Academisfit/status/1868529612554420489

  82. unsorting

  83. novelty-nets

  84. Dropcap Generation With AI

  85. Design Of This Website

  86. https://www.science.org/doi/10.1126/science.ads9158

  87. FlashRNN: Optimizing Traditional RNNs on Modern Hardware

  88. https%253A%252F%252Farxiv.org%252Fabs%252F2412.07752.html

  89. The GAN is dead; long live the GAN! R3GAN: A Modern GAN Baseline

  90. https%253A%252F%252Fopenreview.net%252Fforum%253Fid%253DOrtN9hPP7V.html

  91. Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness

  92. https%253A%252F%252Farxiv.org%252Fabs%252F2408.05446.html

  93. Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification

  94. https%253A%252F%252Farxiv.org%252Fabs%252F2410.00179.html

  95. BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

  96. https%253A%252F%252Farxiv.org%252Fabs%252F2411.13543.html

  97. Why a US AI "Manhattan Project" could backfire: notes from conversations in China

  98. Benjamin Todd

  99. https%253A%252F%252Fbenjamintodd.substack.com%252Fp%252Fwhy-a-us-ai-manhattan-project-could.html

  100. Rating the ratings: Assessing the psychometric quality of rating data

  101. %252Fdoc%252Fstatistics%252Forder%252Fcomparison%252F1980-saal.pdf.html

  102. Evaluating indicators of job performance: Distributions and types of analyses

  103. %252Fdoc%252Feconomics%252F2016-chambers.pdf.html

  104. Dropcap Generation With AI

  105. %252Fdropcap.html

  106. Design Of This Website

  107. %252Fdesign.html