https://lone17.github.io/knowledge/%22Reasonable-people-with-good-intentions-can-still-disagree-over-matters-of-substance.%22 2025-07-09T20:49:19.845Z https://lone17.github.io/knowledge/(some)-functions-are-vectors-(infinite-dimensional-objects) 2024-02-24T19:06:00.000Z https://lone17.github.io/knowledge/AQLM 2024-08-15T05:44:00.000Z https://lone17.github.io/knowledge/Adaptive-KV-cache-pruning-with-selective-features 2025-02-25T20:44:00.000Z https://lone17.github.io/knowledge/Adaptive-LoRA 2024-07-08T22:01:00.000Z https://lone17.github.io/knowledge/Angular-Steering 2025-07-09T20:49:20.034Z https://lone17.github.io/knowledge/Aphrodite 2024-08-15T05:37:00.000Z https://lone17.github.io/knowledge/Applying-to-Ph.D.-Programs-in-Computer-Science---Mor-Harchol-Balter,-CMU 2025-07-09T20:49:20.098Z https://lone17.github.io/knowledge/Approximate-Nearest-Neighbors 2024-02-14T17:32:00.000Z https://lone17.github.io/knowledge/AutoAWQ 2024-02-14T21:30:00.000Z https://lone17.github.io/knowledge/Bertrand's-theorem 2024-02-18T05:45:00.000Z https://lone17.github.io/knowledge/Best-and-Worst-of-both-worlds---combining-LSTM-and-Transformers 2024-07-29T03:14:00.000Z https://lone17.github.io/knowledge/Bring-Windows-features-to-MacOS 2024-07-08T17:09:00.000Z https://lone17.github.io/knowledge/Byte-Pair-Encoding-(BPE) 2024-07-30T04:04:00.000Z https://lone17.github.io/knowledge/Byte-level-BPE 2024-07-30T04:06:00.000Z https://lone17.github.io/knowledge/CTransformers 2024-02-14T22:17:00.000Z https://lone17.github.io/knowledge/Calculate-GPU-memory-requirement-and-tokens-for-any-LLM 2025-07-09T20:49:20.198Z https://lone17.github.io/knowledge/Central-Limit-Theorem 2024-06-13T21:32:00.000Z https://lone17.github.io/knowledge/Changing-MLP-layers-in-Transformers-to-Probabilistic-encoders 2025-07-09T20:49:20.211Z https://lone17.github.io/knowledge/Combining-Modular-Skills-in-Multitask-Learning 2025-07-09T20:49:20.220Z https://lone17.github.io/knowledge/Conformal-prediction 2025-07-09T20:49:20.226Z https://lone17.github.io/knowledge/Connections-of-SVD,-PCA,-eigenvectors-and-eigenvalues 2024-12-01T19:27:00.000Z https://lone17.github.io/knowledge/Controlling-reasoning-duration-with-activation-steering 2025-07-09T20:49:20.292Z https://lone17.github.io/knowledge/Cross-lingual-transfer-by-forced-alignment-of-embeddings-in-different-languages 2025-07-09T20:49:20.300Z https://lone17.github.io/knowledge/Cross-moments-of-a-random-vector 2025-07-09T20:49:20.314Z https://lone17.github.io/knowledge/DFS,-BFS,-Dynamic-Programming-and-LLM-decoding 2025-07-09T20:49:20.320Z https://lone17.github.io/knowledge/Diffusion-language-modeling-with-maximum-semantic-likelihood 2025-07-09T20:49:20.336Z https://lone17.github.io/knowledge/Discriminative-Generative-Learning 2024-06-27T22:52:00.000Z https://lone17.github.io/knowledge/Dynamic-sized-latent-representations 2025-07-09T20:49:20.401Z https://lone17.github.io/knowledge/EXL2 2024-02-14T18:44:00.000Z https://lone17.github.io/knowledge/Efficient-Transformers-with-Dynamic-Token-Pooling 2025-07-09T20:49:20.413Z https://lone17.github.io/knowledge/Euler's-theorem 2024-02-24T19:22:00.000Z https://lone17.github.io/knowledge/Excalidraw/Drawing-2023-12-05-04.02.33.excalidraw 2025-07-09T20:49:20.449Z https://lone17.github.io/knowledge/Excalidraw/Scripts/Downloaded/Auto-Draw-for-Pen 2025-07-09T20:49:20.499Z https://lone17.github.io/knowledge/Excalidraw/Scripts/Downloaded/Hardware-Eraser-Support 2023-12-06T23:05:00.000Z https://lone17.github.io/knowledge/Excalidraw/Scripts/Downloaded/Zoom-to-Fit-Selected-Elements 2023-12-06T22:18:00.000Z https://lone17.github.io/knowledge/Excalidraw/temperature-vs-nucleus-sampling.excalidraw 2023-12-18T19:54:00.000Z https://lone17.github.io/knowledge/Exploiting-the-Bias-Variance-trade-off-for-data-fitting 2025-07-09T20:49:20.530Z https://lone17.github.io/knowledge/Failure-is-a-favour-to-the-future 2025-07-09T20:49:20.533Z https://lone17.github.io/knowledge/Fenwick-Tree 2024-09-14T19:37:00.000Z https://lone17.github.io/knowledge/GCD-Convolution 2025-07-09T20:49:20.539Z https://lone17.github.io/knowledge/GGML 2025-07-09T20:49:20.542Z https://lone17.github.io/knowledge/GGUF 2025-07-09T20:49:20.546Z https://lone17.github.io/knowledge/GPTQ-for-LLaMa 2024-02-14T19:19:00.000Z https://lone17.github.io/knowledge/Graduate-Application-Aid 2025-07-09T20:49:20.559Z https://lone17.github.io/knowledge/Graduate-Applications-Advice---Nathan-Lambert 2025-07-09T20:49:20.565Z https://lone17.github.io/knowledge/Graph-of-Life 2025-07-09T20:49:20.569Z https://lone17.github.io/knowledge/Hierarchical-sliding-window-transformers 2025-07-09T20:49:20.591Z https://lone17.github.io/knowledge/Highlight-Colour-Codings 2025-07-09T20:49:20.596Z https://lone17.github.io/knowledge/How-To-Train-Your-LLM-Efficiently 2023-11-27T17:48:00.000Z https://lone17.github.io/knowledge/Hyrum's-Law 2024-09-29T17:43:00.000Z https://lone17.github.io/knowledge/I-do-things-to-satisfactory. 2024-09-29T17:43:00.000Z https://lone17.github.io/knowledge/I-know-nothing 2024-02-29T20:57:00.000Z https://lone17.github.io/knowledge/IELTS-materials 2025-07-09T20:49:20.616Z https://lone17.github.io/knowledge/Information-Retrieval-service 2025-07-09T20:49:20.620Z https://lone17.github.io/knowledge/Is-an-LLM-a-one-giant-Hidden-Markov-model- 2025-01-29T15:20:00.000Z https://lone17.github.io/knowledge/Just-be.-Smart.---letam.io 2024-08-30T05:26:00.000Z https://lone17.github.io/knowledge/LLM-and-HNSW 2025-01-09T02:24:00.000Z https://lone17.github.io/knowledge/LLM-and-quantum-computing-and-direction-finding---unified-by-superposition 2025-07-09T20:49:20.629Z https://lone17.github.io/knowledge/LLM-generation-is-path-finding-in-activation-space,-each-decoder-block's-processing-is-taking-a-step-in-said-space 2025-07-09T20:26:00.000Z https://lone17.github.io/knowledge/LLMs-development 2025-07-09T20:49:20.633Z https://lone17.github.io/knowledge/Legendre's-conjecture 2025-07-09T20:49:20.636Z https://lone17.github.io/knowledge/LoRA-abliterated 2025-07-09T20:49:20.639Z https://lone17.github.io/knowledge/Local-LLM 2025-07-09T20:49:20.663Z https://lone17.github.io/knowledge/ML-might-be-bad-for-science-and-the-importance-of-understanding-how-ML-works 2025-07-09T20:49:20.698Z https://lone17.github.io/knowledge/Machine-Learning-vocabs 2024-02-11T17:44:00.000Z https://lone17.github.io/knowledge/Mixture-of-Experts 2025-07-09T20:49:20.711Z https://lone17.github.io/knowledge/Mixture-of-Distribution-learning 2024-06-27T22:36:00.000Z https://lone17.github.io/knowledge/Moravec's-paradox 2025-07-09T20:49:20.727Z https://lone17.github.io/knowledge/No-Free-Lunch-theorem 2024-02-21T19:19:00.000Z https://lone17.github.io/knowledge/Nomi-questions 2025-06-19T19:47:00.000Z https://lone17.github.io/knowledge/Problem-solving-by-superpositional-steering 2025-06-29T20:10:00.000Z https://lone17.github.io/knowledge/Pursuit-ignorance,-pursuit-mastery. 2025-07-09T20:49:20.793Z https://lone17.github.io/knowledge/Refusal-behaviour-can-be-controlled-by-turning-a-knob 2025-07-09T20:49:20.916Z https://lone17.github.io/knowledge/Riemannian-Manifolds-and-Fisher-Information 2025-07-09T20:49:21.043Z https://lone17.github.io/knowledge/Rotate-any-vector-to-a-target-angle-in-high-dimensional-space 2025-01-29T20:28:00.000Z https://lone17.github.io/knowledge/Rotate-from-one-vector-to-another-vector-in-high-dimensional-space 2025-07-09T20:49:21.096Z https://lone17.github.io/knowledge/SFT---Supervised-Fine-tuning 2023-12-26T19:34:00.000Z https://lone17.github.io/knowledge/Scaling-Sparse-Fine-Tuning-to-Large-Language-Models 2025-07-09T20:49:21.109Z https://lone17.github.io/knowledge/Segment-Tree 2024-09-26T19:30:00.000Z https://lone17.github.io/knowledge/SentencePiece 2024-07-30T04:16:00.000Z https://lone17.github.io/knowledge/Set-a-deadline-to-end,-do-not-set-a-deadline-to-start. 2025-07-09T20:49:21.131Z https://lone17.github.io/knowledge/Sharded-checkpointing 2023-12-31T02:54:00.000Z https://lone17.github.io/knowledge/Stanford-cheatsheet 2025-07-09T20:49:21.134Z https://lone17.github.io/knowledge/Steering-multiple-behaviours-jointly 2025-07-09T20:49:21.136Z https://lone17.github.io/knowledge/Structure-LLMs-output 2024-07-26T04:09:00.000Z https://lone17.github.io/knowledge/The-Bitter-Lesson 2024-01-30T18:00:00.000Z https://lone17.github.io/knowledge/The-Reparameterization-trick 2025-07-09T20:49:21.213Z https://lone17.github.io/knowledge/The-effect-of-BatchNorm-vs-LayerNorm-vs-RMSNorm 2024-11-19T15:06:00.000Z https://lone17.github.io/knowledge/The-effects-of-neural-net-layers-on-activation-space 2024-10-29T10:08:00.000Z https://lone17.github.io/knowledge/The-only-work-that-really-matters-is-the-work-that-no-one-sees 2024-10-18T17:24:00.000Z https://lone17.github.io/knowledge/The-wrong-way-of-teaching 2024-02-20T03:16:00.000Z https://lone17.github.io/knowledge/Theory-of-activation-space 2024-11-05T05:02:00.000Z https://lone17.github.io/knowledge/Toy-Models-of-Superposition 2024-11-09T15:14:00.000Z https://lone17.github.io/knowledge/Transforming-column-vectors-of-model-weights-to-standard-bases 2024-11-27T03:49:00.000Z https://lone17.github.io/knowledge/Unigram-Tokenization 2024-07-30T04:07:00.000Z https://lone17.github.io/knowledge/Universal-Approximation-Theorems 2024-06-29T17:31:00.000Z https://lone17.github.io/knowledge/Untitled 2025-07-09T20:49:21.302Z https://lone17.github.io/knowledge/VRDSynth 2023-12-07T22:07:00.000Z https://lone17.github.io/knowledge/When-we-think-of-what-could-go-wrong,-we-achieve-so-little. 2025-07-09T20:49:21.355Z https://lone17.github.io/knowledge/WordPiece 2024-07-30T04:07:00.000Z https://lone17.github.io/knowledge/Writing-to-learn 2024-02-29T20:54:00.000Z https://lone17.github.io/knowledge/%60model.eval()%60-vs-%60torch.no_grad()%60 2025-07-09T20:49:21.396Z https://lone17.github.io/knowledge/a-hypothesis-for-the-mechanism-of-reasoning 2025-02-03T11:52:00.000Z https://lone17.github.io/knowledge/alias-in-CMD 2025-07-09T20:49:21.402Z https://lone17.github.io/knowledge/anyway-vs-any-way-vs-anyways 2025-07-09T20:49:21.406Z https://lone17.github.io/knowledge/associative-memory 2025-07-09T20:49:21.409Z https://lone17.github.io/knowledge/auto-start-ssh-agent 2023-11-24T18:11:00.000Z https://lone17.github.io/knowledge/auxiliary-loss-for-language-models 2024-03-03T21:55:00.000Z https://lone17.github.io/knowledge/binary-prefix-trie 2024-09-01T04:31:00.000Z https://lone17.github.io/knowledge/bubble-sort 2024-07-25T19:30:00.000Z https://lone17.github.io/knowledge/career-advices-from-Terrance-Tao 2024-02-13T20:35:00.000Z https://lone17.github.io/knowledge/chat-agent-with-action-planning 2024-08-13T04:14:00.000Z https://lone17.github.io/knowledge/combination 2025-07-09T20:49:21.427Z https://lone17.github.io/knowledge/common-bit-manipulation 2025-07-09T20:49:21.428Z https://lone17.github.io/knowledge/completed-thoughts/Be-motivated-by-the-action,-not-by-the-goal.-Constant-action-gives-constant-progress,-which-is-a-recurring-source-of-dopamine. 2024-02-05T02:57:00.000Z https://lone17.github.io/knowledge/completed-thoughts/Cinnamon-should-rethink-research 2025-07-09T20:49:21.434Z https://lone17.github.io/knowledge/completed-thoughts/Don't-seek-to-understand,-seek-for-a-satisfying-intuition.-Understanding-is-when-you-know-something-makes-sense,-intuition-is-when-you-can-feel-the-sense-that-was-made. 2024-02-02T20:08:00.000Z https://lone17.github.io/knowledge/completed-thoughts/I-have-a-constant-pressure-of-how-much-I-don't-know-and-how-much-more-I-don't-even-know-that-I-don't-know. 2025-07-09T20:49:21.440Z https://lone17.github.io/knowledge/completed-thoughts/Live-intentionally,-spend-time-intentionally. 2024-02-08T20:40:00.000Z https://lone17.github.io/knowledge/completed-thoughts/The-problem-with-modelling-the-human-brain 2024-01-30T19:57:00.000Z https://lone17.github.io/knowledge/completed-thoughts/a-different-type-of-intelligence 2024-01-30T17:58:00.000Z https://lone17.github.io/knowledge/completed-thoughts/how-Obsidian-is-good-for-me 2024-01-30T18:29:00.000Z https://lone17.github.io/knowledge/completed-thoughts/my-favourite-activity-is-thinking 2025-07-09T20:49:21.458Z https://lone17.github.io/knowledge/completed-thoughts/what-knowledge-gives-me 2025-07-09T20:49:21.460Z https://lone17.github.io/knowledge/completed-thoughts/working-in-AI-and-understanding-statistics 2024-01-29T05:31:00.000Z https://lone17.github.io/knowledge/completed-thoughts/write-your-thoughts-down 2024-01-30T18:14:00.000Z https://lone17.github.io/knowledge/complex-number-vs-2d-vectors 2024-02-24T19:48:00.000Z https://lone17.github.io/knowledge/count-the-GCD-values-of-all-pairs 2024-07-29T03:14:00.000Z https://lone17.github.io/knowledge/coupling-object-and-relation-representation 2025-07-09T20:49:19.855Z https://lone17.github.io/knowledge/cs/computer-architect/IEEE-754-floating-point 2025-07-09T20:49:19.922Z https://lone17.github.io/knowledge/cs/os/wsl/relay-ssh-agent-and-gpg-agent-in-windows 2025-07-09T20:49:19.997Z https://lone17.github.io/knowledge/cs/os/wsl/set-automounts-option-for-WSL 2025-07-09T20:49:20.012Z https://lone17.github.io/knowledge/cs/os/wsl/symlink-windows-exe-to-wsl 2025-07-09T20:49:20.020Z https://lone17.github.io/knowledge/curse-of-dimenstionality 2025-07-09T20:49:20.026Z https://lone17.github.io/knowledge/detect-if-PATH-has-a-specific-directory-entry-in-it 2023-10-23T22:20:00.000Z https://lone17.github.io/knowledge/diffusion-is-path-finding-in-gradient-space-of-data-distribution-using-Langevin-sampling 2025-07-09T20:49:20.034Z https://lone17.github.io/knowledge/discriminative-and-generative-models 2024-02-21T17:10:00.000Z https://lone17.github.io/knowledge/distill-from-AR-LM-to-diffusion-LM 2025-07-09T20:28:00.000Z https://lone17.github.io/knowledge/eigen-values-and-Page-Rank 2025-03-02T20:29:00.000Z https://lone17.github.io/knowledge/generate-primes 2024-02-18T04:27:00.000Z https://lone17.github.io/knowledge/generate-random-unit-vectors 2024-06-11T22:59:00.000Z https://lone17.github.io/knowledge/heighten-a-behaviour-in-LLMs 2025-07-09T20:49:20.141Z https://lone17.github.io/knowledge/how-does-smaller-versions-of-the-same-llm-(3b,-7b,-13b,-etc.)-are-trained 2024-03-03T22:00:00.000Z https://lone17.github.io/knowledge/how-to-%22average%22-a-set-of-vectors 2025-07-09T20:49:20.194Z https://lone17.github.io/knowledge/hybrid-of-full-weight-update-and-PEFT 2024-02-25T18:26:00.000Z https://lone17.github.io/knowledge/incompleted-thoughts/(2x2)D-attention 2025-07-09T20:49:20.203Z https://lone17.github.io/knowledge/incompleted-thoughts/A-pen-that-can-write-on-any-surface-and-the-content-will-be-recorded-in-an-app 2025-07-09T20:49:20.208Z https://lone17.github.io/knowledge/incompleted-thoughts/Dimensions-of-language 2025-07-09T20:49:20.218Z https://lone17.github.io/knowledge/incompleted-thoughts/QA-on-documents 2025-07-09T20:49:20.225Z https://lone17.github.io/knowledge/incompleted-thoughts/Related-work-writing-tool 2025-07-09T20:49:20.227Z https://lone17.github.io/knowledge/incompleted-thoughts/The-relationship-between-knowledge-and-creativity 2024-01-23T17:10:00.000Z https://lone17.github.io/knowledge/incompleted-thoughts/ads-that-appear-in-game-environment 2025-07-09T20:49:20.292Z https://lone17.github.io/knowledge/incompleted-thoughts/auto-suggest-which-paper-to-cite 2025-07-09T20:49:20.297Z https://lone17.github.io/knowledge/incompleted-thoughts/document-layout-synthesis 2025-07-09T20:49:20.300Z https://lone17.github.io/knowledge/incompleted-thoughts/dynamic-computation-for-deep-learning-models 2025-07-09T20:49:20.305Z https://lone17.github.io/knowledge/incompleted-thoughts/is-LLaMa-better-than-LLaMa-2 2025-07-09T20:49:20.307Z https://lone17.github.io/knowledge/incompleted-thoughts/network-of-documents-connected-by-small-scale-ideas 2025-07-09T20:49:20.308Z https://lone17.github.io/knowledge/incompleted-thoughts/random-attention 2025-07-09T20:49:20.314Z https://lone17.github.io/knowledge/incompleted-thoughts/swap-windows-in-2-monitors 2025-07-09T20:49:20.320Z https://lone17.github.io/knowledge/incompleted-thoughts/the-self-attention-equation-similar-to-Newton's-gravity-equation 2025-07-09T20:49:20.322Z https://lone17.github.io/knowledge/ 2024-11-29T12:20:00.000Z https://lone17.github.io/knowledge/it's-better-to-learn-unique-skills-instead-of-common-ones 2024-02-24T21:08:00.000Z https://lone17.github.io/knowledge/karabiner-complex-modification-to-make-macOS-feel-more-like-Windows 2024-07-23T03:03:00.000Z https://lone17.github.io/knowledge/learning-by-interacting-with-oneself 2025-07-09T20:49:20.342Z https://lone17.github.io/knowledge/light-travels-in-all-possible-paths-to-get-from-A-to-B 2025-07-09T20:49:20.347Z https://lone17.github.io/knowledge/limit-equals-to-e 2025-07-09T20:49:20.390Z https://lone17.github.io/knowledge/literature-notes/%22the-effort-to-use-machines-to-try-to-mimic-human-reasoning-is-both-foolish-and-dangerous%22 2025-07-09T20:49:20.395Z https://lone17.github.io/knowledge/literature-notes/1's-complement 2025-07-09T20:49:20.413Z https://lone17.github.io/knowledge/literature-notes/2's-complement 2025-07-09T20:49:20.433Z https://lone17.github.io/knowledge/literature-notes/Advices-on-building-LLMs 2023-12-21T21:46:00.000Z https://lone17.github.io/knowledge/literature-notes/All-models-are-wrong.-Some-models-are-useful. 2023-12-22T19:00:00.000Z https://lone17.github.io/knowledge/literature-notes/Bayesians-are-frequentists 2025-07-09T20:49:20.500Z https://lone17.github.io/knowledge/literature-notes/Career-Advice,-Reading-Research-Papers-by-Andrew-Ng 2025-07-09T20:49:20.508Z https://lone17.github.io/knowledge/literature-notes/Do-important-work. 2025-07-09T20:49:20.512Z https://lone17.github.io/knowledge/literature-notes/Earth-rotation-can't-be-used-for-time-keeping 2023-12-22T00:04:00.000Z https://lone17.github.io/knowledge/literature-notes/Goodhart's-Law 2023-12-20T20:06:00.000Z https://lone17.github.io/knowledge/literature-notes/If-I-can't-find-a-path-I'll-make-one 2025-07-09T20:49:20.535Z https://lone17.github.io/knowledge/literature-notes/Joy-is-be-able-to-see-things-that-people-couldn't. 2025-07-09T20:49:20.538Z https://lone17.github.io/knowledge/literature-notes/LLMs-shortcomings 2023-12-27T17:59:00.000Z https://lone17.github.io/knowledge/literature-notes/MosaicML-Foundry 2023-12-21T22:39:00.000Z https://lone17.github.io/knowledge/literature-notes/MosaicML-Streaming-Data-Loader 2023-11-30T21:58:00.000Z https://lone17.github.io/knowledge/literature-notes/MosaicML-tools 2023-12-21T21:56:00.000Z https://lone17.github.io/knowledge/literature-notes/Omnivore/*Refusal-in-LLMs-is-mediated-by-a-single-direction-%E2%80%94-LessWrong 2024-10-21T07:22:00.000Z https://lone17.github.io/knowledge/literature-notes/Omnivore/LoRA-Fine-tuning-Efficiently-Undoes-Safety-Training-from-Llama-2-Chat-70B-%E2%80%94-LessWrong 2024-10-21T04:58:00.000Z https://lone17.github.io/knowledge/literature-notes/Open-Problems-in-the-Theory-of-Deep-Learning---MITCBMM 2025-07-09T20:49:20.931Z https://lone17.github.io/knowledge/literature-notes/Principles-of-Success-by-Ray-Dalio 2024-02-09T20:03:00.000Z https://lone17.github.io/knowledge/literature-notes/Sidereal-day 2023-12-21T23:59:00.000Z https://lone17.github.io/knowledge/literature-notes/Survey-of-LLMs 2025-07-09T20:49:20.946Z https://lone17.github.io/knowledge/literature-notes/The-Earth-is-slowing-down 2023-12-22T00:07:00.000Z https://lone17.github.io/knowledge/literature-notes/The-Unknown-Unknown 2025-07-09T20:49:20.994Z https://lone17.github.io/knowledge/literature-notes/The-length-of-a-solar-day-is-not-actually-24-hours 2023-12-22T00:02:00.000Z https://lone17.github.io/knowledge/literature-notes/The-opposite-of-a-profound-truth 2025-07-09T20:49:21.002Z https://lone17.github.io/knowledge/literature-notes/The-productivity-of-a-knowledge-worker-should-be-tracked-by-how-many-permanent-notes-you-produce-a-day. 2023-11-24T18:38:00.000Z https://lone17.github.io/knowledge/literature-notes/The-pursuit-of-ignorance. 2025-07-09T20:49:21.006Z https://lone17.github.io/knowledge/literature-notes/Things-that-change-the-rotation-of-the-Earth 2023-12-22T00:09:00.000Z https://lone17.github.io/knowledge/literature-notes/Training-and-Fine-tuning-LLMs---W-and-B-course 2023-12-21T21:43:00.000Z https://lone17.github.io/knowledge/literature-notes/What-would-you-do-even-if-you-know-you-would-fail 2024-01-19T18:59:00.000Z https://lone17.github.io/knowledge/literature-notes/You-just-can't-compete-with-someone-who-is-having-fun 2024-02-06T20:55:00.000Z https://lone17.github.io/knowledge/literature-notes/fleeting-notes 2023-11-24T18:55:00.000Z https://lone17.github.io/knowledge/literature-notes/kasten-(boxes) 2025-07-09T20:49:21.046Z https://lone17.github.io/knowledge/literature-notes/literature-notes 2025-07-09T20:49:21.063Z https://lone17.github.io/knowledge/literature-notes/llama-cpp-python 2025-07-09T20:49:21.091Z https://lone17.github.io/knowledge/literature-notes/llama-cpp 2025-07-09T20:49:21.097Z https://lone17.github.io/knowledge/literature-notes/offset-binary 2025-07-09T20:49:21.118Z https://lone17.github.io/knowledge/literature-notes/papers/BAM!-Just-Like-That---Simple-and-Efficient-Parameter-Upcycling-for-Mixture-of-Experts 2025-07-09T20:49:21.123Z https://lone17.github.io/knowledge/literature-notes/papers/Beyond-neural-scaling-laws---beating-power-law-scaling-via-data-pruning 2025-07-09T20:49:21.130Z https://lone17.github.io/knowledge/literature-notes/papers/CAMEx---Curvature-Aware-Merging-of-Experts 2025-07-09T20:49:21.142Z https://lone17.github.io/knowledge/literature-notes/permanent-notes 2023-11-24T18:56:00.000Z https://lone17.github.io/knowledge/literature-notes/pipelining 2025-07-09T20:49:21.214Z https://lone17.github.io/knowledge/literature-notes/risc-vs-cisc 2025-07-09T20:49:21.247Z https://lone17.github.io/knowledge/literature-notes/sign-magnitude 2025-07-09T20:49:21.300Z https://lone17.github.io/knowledge/literature-notes/syncthing 2025-07-09T20:49:21.312Z https://lone17.github.io/knowledge/literature-notes/web-clipper/A-Mathematical-Framework-for-Transformer-Circuits 2024-12-03T17:00:00.000Z https://lone17.github.io/knowledge/literature-notes/web-clipper/Memory-efficient-Model-Weight-Loading 2024-11-13T17:00:00.000Z https://lone17.github.io/knowledge/literature-notes/zettel-(notes) 2025-07-09T20:49:21.390Z https://lone17.github.io/knowledge/literature-notes/zettlekasten 2023-11-24T19:29:00.000Z https://lone17.github.io/knowledge/literature-notes/zotero/A-Language-Model's-Guide-Through-Latent-Space 2025-07-09T20:49:21.417Z https://lone17.github.io/knowledge/literature-notes/zotero/A-Statistical-Physics-of-Language-Model-Reasoning 2025-07-09T20:49:21.427Z https://lone17.github.io/knowledge/literature-notes/zotero/Are-Emergent-Abilities-of-Large-Language-Models-a-Mirage 2025-07-09T20:49:21.439Z https://lone17.github.io/knowledge/literature-notes/zotero/BAM!-Just-Like-That---Simple-and-Efficient-Parameter-Upcycling-for-Mixture-of-Experts 2025-07-09T20:49:21.456Z https://lone17.github.io/knowledge/literature-notes/zotero/CAMEx---Curvature-Aware-Merging-of-Experts 2025-07-09T20:49:21.494Z https://lone17.github.io/knowledge/literature-notes/zotero/Generative-Modeling-by-Estimating-Gradients-of-the-Data-Distribution 2025-07-09T20:49:21.509Z https://lone17.github.io/knowledge/literature-notes/zotero/Harnessing-the-Universal-Geometry-of-Embeddings 2025-07-09T20:49:21.521Z https://lone17.github.io/knowledge/literature-notes/zotero/Information-Gravity---A-Field-Theoretic-Model-for-Token-Selection-in-Large-Language-Models 2025-07-09T20:49:21.530Z https://lone17.github.io/knowledge/literature-notes/zotero/Linear-Representations-of-Sentiment-in-Large-Language-Models 2025-07-09T20:49:21.537Z https://lone17.github.io/knowledge/literature-notes/zotero/Mathematical-Models-of-Computation-in-Superposition 2025-07-09T20:49:21.545Z https://lone17.github.io/knowledge/literature-notes/zotero/Mechanistic-Interpretability-for-AI-Safety----A-Review 2024-07-23T09:20:00.000Z https://lone17.github.io/knowledge/literature-notes/zotero/On-the-Complexity-of-Neural-Computation-in-Superposition 2025-07-09T20:49:21.568Z https://lone17.github.io/knowledge/literature-notes/zotero/Programming-Refusal-with-Conditional-Activation-Steering 2025-07-09T20:49:21.576Z https://lone17.github.io/knowledge/literature-notes/zotero/Reasoning-by-Superposition---A-Theoretical-Perspective-on-Chain-of-Continuous-Thought 2025-07-09T20:49:21.583Z https://lone17.github.io/knowledge/literature-notes/zotero/Refusal-in-Language-Models-Is-Mediated-by-a-Single-Direction 2025-07-09T20:49:21.592Z https://lone17.github.io/knowledge/literature-notes/zotero/Representation-Engineering---A-Top-Down-Approach-to-AI-Transparency 2025-07-09T20:49:21.598Z https://lone17.github.io/knowledge/literature-notes/zotero/Scaling-Laws-for-Fine-Grained-Mixture-of-Experts 2025-07-09T20:49:21.604Z https://lone17.github.io/knowledge/literature-notes/zotero/Steering-Language-Models-With-Activation-Engineering 2025-07-09T20:49:21.610Z https://lone17.github.io/knowledge/literature-notes/zotero/Superposition-of-many-models-into-one 2025-07-09T20:49:21.617Z https://lone17.github.io/knowledge/literature-notes/zotero/The-Linear-Representation-Hypothesis-and-the-Geometry-of-Large-Language-Models 2025-07-09T20:49:21.624Z https://lone17.github.io/knowledge/literature-notes/zotero/Training-Large-Language-Models-to-Reason-in-a-Continuous-Latent-Space 2025-07-09T20:49:21.636Z https://lone17.github.io/knowledge/literature-notes/zotero/Transformer-Feed-Forward-Layers-Are-Key-Value-Memories 2024-07-23T09:20:00.000Z https://lone17.github.io/knowledge/literature-notes/zotero/Understanding-Reasoning-in-Thinking-Language-Models-via-Steering-Vectors 2025-07-09T20:49:21.657Z https://lone17.github.io/knowledge/literature-notes/zotero/Universal-and-Transferable-Adversarial-Attacks-on-Aligned-Language-Models 2024-07-23T09:20:00.000Z https://lone17.github.io/knowledge/literature-notes/zotero/Zotero-Integration-template 2024-07-23T09:20:00.000Z https://lone17.github.io/knowledge/litterature-notes/Omnivore/Organize-your-Omnivore-library-with-labels 2025-07-09T20:49:21.684Z https://lone17.github.io/knowledge/local-AI-server 2024-06-12T20:15:00.000Z https://lone17.github.io/knowledge/me 2025-07-09T20:49:21.696Z https://lone17.github.io/knowledge/merge-sort 2024-07-25T19:23:00.000Z https://lone17.github.io/knowledge/modular-multi-modal-hard-routing 2025-07-09T20:49:21.708Z https://lone17.github.io/knowledge/my-hybrid-sort 2024-07-25T19:32:00.000Z https://lone17.github.io/knowledge/my-naive-theory-on-ML 2024-09-29T03:39:00.000Z https://lone17.github.io/knowledge/my-systematic-errors-in-English 2024-03-03T21:23:00.000Z https://lone17.github.io/knowledge/overfitting-underfitting-and-variance-bias 2024-02-11T18:30:00.000Z https://lone17.github.io/knowledge/permanent-notes/A-day-is-not-actually-24h-long 2023-12-22T00:17:00.000Z https://lone17.github.io/knowledge/permanent-notes/ALiBi 2023-11-30T23:10:00.000Z https://lone17.github.io/knowledge/permanent-notes/Activation-Checkpointing 2023-12-22T18:18:00.000Z https://lone17.github.io/knowledge/permanent-notes/Adam 2023-12-22T23:55:00.000Z https://lone17.github.io/knowledge/permanent-notes/Aho-Corasick-algorithm 2024-07-07T05:43:00.000Z https://lone17.github.io/knowledge/permanent-notes/Bayesian-statistics 2025-07-09T20:49:19.829Z https://lone17.github.io/knowledge/permanent-notes/Building-your-own-tokenizers 2023-12-22T23:23:00.000Z https://lone17.github.io/knowledge/permanent-notes/Checkpointing-for-LLM-training 2023-12-23T20:48:00.000Z https://lone17.github.io/knowledge/permanent-notes/Chinchilla-scaling-laws 2023-12-21T21:15:00.000Z https://lone17.github.io/knowledge/permanent-notes/Choosing-architecture-for-training-LLM 2023-12-22T20:54:00.000Z https://lone17.github.io/knowledge/permanent-notes/Cost-to-train-a-LLM 2023-12-22T17:42:00.000Z https://lone17.github.io/knowledge/permanent-notes/Data-parallelism 2023-12-22T19:10:00.000Z https://lone17.github.io/knowledge/permanent-notes/Dijkstra-algorithm 2024-07-27T05:05:00.000Z https://lone17.github.io/knowledge/permanent-notes/Fermat's-2-square-theorem 2025-07-09T20:49:20.111Z https://lone17.github.io/knowledge/permanent-notes/HFU---Hardware-FLOPs-Utilization 2023-12-22T18:30:00.000Z https://lone17.github.io/knowledge/permanent-notes/HumanEval-Pros-and-Cons 2023-12-18T20:55:00.000Z https://lone17.github.io/knowledge/permanent-notes/Intuition-on-understanding-the-meaning-of-variance-and-bias-for-Machine-Learning 2023-12-18T17:32:00.000Z https://lone17.github.io/knowledge/permanent-notes/KMP---Knuth-Morris-Pratt 2024-01-14T17:16:00.000Z https://lone17.github.io/knowledge/permanent-notes/LLM-fine-tuning 2023-12-23T21:27:00.000Z https://lone17.github.io/knowledge/permanent-notes/LLM-parallelism-strategies 2025-07-09T20:49:20.245Z https://lone17.github.io/knowledge/permanent-notes/LLM-sampling-strategy 2023-12-18T20:13:00.000Z https://lone17.github.io/knowledge/permanent-notes/LLMs-evaluation 2023-12-23T22:00:00.000Z https://lone17.github.io/knowledge/permanent-notes/LSP---Longest-Suffix-which-is-also-a-prefix 2025-07-09T20:49:20.336Z https://lone17.github.io/knowledge/permanent-notes/Lagrange's-4-square-theorem 2025-07-09T20:49:20.344Z https://lone17.github.io/knowledge/permanent-notes/Legendre's-3-square-theorem 2025-07-09T20:49:20.350Z https://lone17.github.io/knowledge/permanent-notes/LoRA 2023-12-23T21:36:00.000Z https://lone17.github.io/knowledge/permanent-notes/Logistics-of-Data-Loading-for-LLMs-training 2023-12-21T22:03:00.000Z https://lone17.github.io/knowledge/permanent-notes/MFU---Model-FLOPs-Utilization 2023-12-22T18:27:00.000Z https://lone17.github.io/knowledge/permanent-notes/Mahonian-numbers 2025-07-09T20:49:20.425Z https://lone17.github.io/knowledge/permanent-notes/Memory-usage-for-LLM-training 2023-12-22T19:05:00.000Z https://lone17.github.io/knowledge/permanent-notes/Pipeline-parallelism 2023-12-22T19:36:00.000Z https://lone17.github.io/knowledge/permanent-notes/Problems-during-LLMs-pre-training 2023-12-23T20:19:00.000Z https://lone17.github.io/knowledge/permanent-notes/RLHF 2023-12-23T21:31:00.000Z https://lone17.github.io/knowledge/permanent-notes/Rabin-Karp 2024-01-23T21:12:00.000Z https://lone17.github.io/knowledge/permanent-notes/RoPE---Rotary-Position-Embeddings 2023-12-22T23:08:00.000Z https://lone17.github.io/knowledge/permanent-notes/Techniques-for-improving-the-stability-of-training-large-ML-models 2025-07-09T20:49:20.519Z https://lone17.github.io/knowledge/permanent-notes/Tensor-parallelism 2023-12-22T19:19:00.000Z https://lone17.github.io/knowledge/permanent-notes/The-ability-to-make-analogies-indicates-intelligence.-If-it-helps-you-understanding-things,-don't-be-afraid-of-making-too-many-analogies. 2025-07-09T20:49:20.524Z https://lone17.github.io/knowledge/permanent-notes/To-curb-one's-own-ignorance-is-a-joy-cherished-only-by-the-most-restless-of-minds. 2023-12-31T00:01:00.000Z https://lone17.github.io/knowledge/permanent-notes/What-can't-be-done-by-an-AI-will-be-done-by-many-AIs-working-together. 2025-07-09T20:49:20.527Z https://lone17.github.io/knowledge/permanent-notes/Z-function 2024-02-04T05:12:00.000Z https://lone17.github.io/knowledge/permanent-notes/ZeRO---Zero-Redundancy-Optimizer 2023-12-22T20:11:00.000Z https://lone17.github.io/knowledge/permanent-notes/classical-probability 2025-07-09T20:49:20.556Z https://lone17.github.io/knowledge/permanent-notes/descent 2025-07-09T20:49:20.559Z https://lone17.github.io/knowledge/permanent-notes/frequentist-statistics 2025-07-09T20:49:20.564Z https://lone17.github.io/knowledge/permanent-notes/frequentist-vs-Bayesian 2024-01-28T20:31:00.000Z https://lone17.github.io/knowledge/permanent-notes/hash 2025-07-09T20:49:20.599Z https://lone17.github.io/knowledge/permanent-notes/insertion-sort 2023-12-03T18:44:00.000Z https://lone17.github.io/knowledge/permanent-notes/inversion 2025-07-09T20:49:20.608Z https://lone17.github.io/knowledge/permanent-notes/likelihood-function 2025-07-09T20:49:20.613Z https://lone17.github.io/knowledge/permanent-notes/major-index 2025-07-09T20:49:20.618Z https://lone17.github.io/knowledge/permanent-notes/modular-multiplicative-inverse 2024-01-23T20:51:00.000Z https://lone17.github.io/knowledge/permanent-notes/nucleus-sampling-(top_p) 2023-12-18T19:45:00.000Z https://lone17.github.io/knowledge/permanent-notes/obsidian-backup 2023-11-24T18:29:00.000Z https://lone17.github.io/knowledge/permanent-notes/obsidian-sync 2023-11-24T18:28:00.000Z https://lone17.github.io/knowledge/permanent-notes/palindrome-substrings 2025-07-09T20:49:20.667Z https://lone17.github.io/knowledge/permanent-notes/pattern-searching 2025-07-09T20:49:20.698Z https://lone17.github.io/knowledge/permanent-notes/permutation 2025-07-09T20:49:20.703Z https://lone17.github.io/knowledge/permanent-notes/perplexity-vs-entropy 2025-07-09T20:49:20.709Z https://lone17.github.io/knowledge/permanent-notes/polynomial-rolling-hash 2024-01-23T20:05:00.000Z https://lone17.github.io/knowledge/permanent-notes/principle-of-difference 2025-07-09T20:49:20.733Z https://lone17.github.io/knowledge/permanent-notes/probability-vs-likelihood 2025-07-09T20:49:20.738Z https://lone17.github.io/knowledge/permanent-notes/rolling-hash 2025-07-09T20:49:20.793Z https://lone17.github.io/knowledge/permanent-notes/symlink-windows-exe-to-wsl 2025-07-09T20:49:20.798Z https://lone17.github.io/knowledge/permanent-notes/temperature-sampling 2023-12-18T20:02:00.000Z https://lone17.github.io/knowledge/permanent-notes/union-find 2025-07-09T20:49:20.812Z https://lone17.github.io/knowledge/priority-queue 2025-07-09T20:49:20.825Z https://lone17.github.io/knowledge/profile-vs-rc-scripts 2023-10-23T21:56:00.000Z https://lone17.github.io/knowledge/programming-interview-questions-to-ask 2025-01-31T17:50:00.000Z https://lone17.github.io/knowledge/python-max-heap 2025-07-09T20:49:20.834Z https://lone17.github.io/knowledge/quantum-computing-deals-with-directions 2025-07-09T20:49:20.838Z https://lone17.github.io/knowledge/quick-sort 2024-07-25T19:23:00.000Z https://lone17.github.io/knowledge/random-unit-vectors-in-high-dimension-are-nearly-orthogonal 2024-06-11T21:47:00.000Z https://lone17.github.io/knowledge/related-concepts-might-be-packed-in-a-low-dimensional-subspace 2025-01-28T16:29:00.000Z https://lone17.github.io/knowledge/relay-ssh-agent-and-gpg-agent-in-windows 2025-07-09T20:49:20.894Z https://lone17.github.io/knowledge/research-interests 2024-02-12T18:29:00.000Z https://lone17.github.io/knowledge/run-command-on-a-remote 2025-07-09T20:49:20.905Z https://lone17.github.io/knowledge/safetensor 2024-02-14T19:54:00.000Z https://lone17.github.io/knowledge/set-automounts-option-for-WSL 2025-07-09T20:49:20.920Z https://lone17.github.io/knowledge/setup-pyenv 2025-07-09T20:49:20.925Z https://lone17.github.io/knowledge/show-all-files-cmd 2025-07-09T20:49:20.927Z https://lone17.github.io/knowledge/speculative-decoding 2025-07-09T20:49:20.929Z https://lone17.github.io/knowledge/stupid-things 2025-07-09T20:49:20.934Z https://lone17.github.io/knowledge/subfractorial 2025-07-09T20:49:20.942Z https://lone17.github.io/knowledge/the-type-of-system-design-philosophy-that-I-like 2025-07-09T20:49:20.947Z https://lone17.github.io/knowledge/todo/AI-resources 2025-07-09T20:49:20.953Z https://lone17.github.io/knowledge/todo/AQLM 2024-08-15T05:44:00.000Z https://lone17.github.io/knowledge/todo/AWQ 2024-02-14T18:43:00.000Z https://lone17.github.io/knowledge/todo/AutoGPTQ 2024-02-14T19:00:00.000Z https://lone17.github.io/knowledge/todo/BF16---brain-floating-point 2023-12-23T22:07:00.000Z https://lone17.github.io/knowledge/todo/Bias-Complexity-tradeoff 2024-02-21T20:31:00.000Z https://lone17.github.io/knowledge/todo/Continuous-Batching 2024-08-15T05:42:00.000Z https://lone17.github.io/knowledge/todo/Control-LLM-generation 2025-07-09T20:49:21.026Z https://lone17.github.io/knowledge/todo/ExLlamaV2 2024-02-14T18:59:00.000Z https://lone17.github.io/knowledge/todo/Excellent-explanation-of-the-Euler-equation 2025-07-09T20:49:21.060Z https://lone17.github.io/knowledge/todo/Expressivity-and-Universal-Approximation-Theorems 2024-05-06T20:18:00.000Z https://lone17.github.io/knowledge/todo/FSDP---Fully-Sharded-Data-Parallel 2023-12-22T20:10:00.000Z https://lone17.github.io/knowledge/todo/From-Autoencoder-to-Beta-VAE 2024-11-16T17:00:00.000Z https://lone17.github.io/knowledge/todo/GPT4All 2025-07-09T20:49:21.098Z https://lone17.github.io/knowledge/todo/GPTQ 2025-07-09T20:49:21.103Z https://lone17.github.io/knowledge/todo/Grouped-query-Attention-(GQA) 2024-02-14T18:55:00.000Z https://lone17.github.io/knowledge/todo/Gumbel-sigmoid 2025-07-09T20:49:21.114Z https://lone17.github.io/knowledge/todo/Hierarchical-Navigable-Small-Worlds-(HNSW) 2024-02-14T17:13:00.000Z https://lone17.github.io/knowledge/todo/KV-Cache 2024-08-15T05:44:00.000Z https://lone17.github.io/knowledge/todo/LLM101n---Course-by-Andrej-Kapathy 2025-07-09T20:49:21.122Z https://lone17.github.io/knowledge/todo/Lessons-learnt-for-training-LLM-(from-bigscience) 2025-07-09T20:49:21.127Z https://lone17.github.io/knowledge/todo/Locally-Typical-Sampling 2024-08-15T05:43:00.000Z https://lone17.github.io/knowledge/todo/MLC-LLM 2025-07-09T20:49:21.131Z https://lone17.github.io/knowledge/todo/Mechanistic-Interpretability 2025-07-09T20:49:21.197Z https://lone17.github.io/knowledge/todo/Mirostat 2024-08-15T05:43:00.000Z https://lone17.github.io/knowledge/todo/Paged-Attention 2025-07-09T20:49:21.223Z https://lone17.github.io/knowledge/todo/QuIP 2024-02-14T22:27:00.000Z https://lone17.github.io/knowledge/todo/RAG 2025-07-09T20:49:21.231Z https://lone17.github.io/knowledge/todo/Smoothquant+ 2024-08-15T05:44:00.000Z https://lone17.github.io/knowledge/todo/SqueezeLLM 2025-07-09T20:49:21.236Z https://lone17.github.io/knowledge/todo/Tail-Free-Sampling 2024-08-15T05:44:00.000Z https://lone17.github.io/knowledge/todo/To-read 2025-07-09T20:49:21.240Z https://lone17.github.io/knowledge/todo/Why-embeddings-are-added,-not-concatenated 2024-04-17T21:16:00.000Z https://lone17.github.io/knowledge/todo/graphical-model 2025-07-09T20:49:21.243Z https://lone17.github.io/knowledge/todo/great-resources 2025-07-09T20:49:21.245Z https://lone17.github.io/knowledge/todo/new-English-words 2025-07-09T20:49:21.248Z https://lone17.github.io/knowledge/todo/quantization 2025-07-09T20:49:21.249Z https://lone17.github.io/knowledge/todo/retrival 2024-01-04T20:50:00.000Z https://lone17.github.io/knowledge/todo/task-arithmetic 2025-07-09T20:49:21.254Z https://lone17.github.io/knowledge/todo/text-chunking-techniques 2025-07-09T20:49:21.256Z https://lone17.github.io/knowledge/todo/the-brilliance-of-transformers'-sinusoidal-positional-embeddings 2025-07-09T20:49:21.258Z https://lone17.github.io/knowledge/todo/uncensor-LLMs 2025-07-09T20:49:21.262Z https://lone17.github.io/knowledge/tokenizers-for-LLMs 2024-07-30T03:25:00.000Z https://lone17.github.io/knowledge/trie 2025-07-09T20:49:21.296Z https://lone17.github.io/knowledge/vLLM 2025-07-09T20:49:21.300Z https://lone17.github.io/knowledge/vector-database 2024-01-02T03:35:00.000Z https://lone17.github.io/knowledge/vector-magnitude-in-LLMs-acts-as-a-filter 2025-07-09T20:49:21.308Z https://lone17.github.io/knowledge/vector-space 2024-02-24T20:50:00.000Z https://lone17.github.io/knowledge/vimium-c-configs 2024-07-29T02:41:00.000Z https://lone17.github.io/knowledge/what-ML-models-learns-and-what's-the-real-solution 2025-07-09T20:49:21.353Z https://lone17.github.io/knowledge/which-features-represented-by-Attention-layers-vs-by-MLP-layers 2024-12-03T10:07:00.000Z https://lone17.github.io/knowledge/why-I-like-ML 2025-07-09T20:49:21.395Z https://lone17.github.io/knowledge/yet-another-hypothesis-on-the-mechanism-of-LLMs 2025-07-09T20:49:21.401Z