/notes/cot-paper-reading/ 2026-05-31T00:00:00+00:00 /notes/important-links/ 2026-06-01T00:00:00+00:00 /notes/world-model-lecture/ 2026-06-02T00:00:00+00:00 /notes/deep-learning-our-miraculous-year-19901991/ 2026-06-03T00:00:00+00:00 /notes/deep-neural-network-properties/ 2026-06-04T00:00:00+00:00 /notes/graph-rag/ 2026-06-12T00:00:00+00:00 /notes/differential-neural-computer/ 2026-06-13T00:00:00+00:00 /notes/visualizing-mnist-dataset/ 2026-06-13T00:00:00+00:00 /notes/vanishing-gradients/ 2026-06-13T00:00:00+00:00 /notes/llm-a-survey/ 2026-06-14T00:00:00+00:00 /notes/information-theory/ 2026-06-16T00:00:00+00:00 /notes/current-open-research/ 2026-06-17T00:00:00+00:00 /notes/maistros-a-greek-llm-through-knowledge-distillation/ 2026-06-17T00:00:00+00:00 /notes/debating-with-more-persuasive-llms-leads-to-more-truthful-answers/ 2026-06-18T00:00:00+00:00 /notes/noticing-the-watcher-llm-infer-surveillance-from-blocked-feedback/ 2026-06-18T00:00:00+00:00 /notes/an-introduction-to-mechanistic-interpretability-neel-nanda-iaseai-2025/ 2026-06-19T00:00:00+00:00 /notes/gao-jun-et-al-representation-degeneration-problem-in-training-natural-language-generation-models/ 2026-06-19T00:00:00+00:00 /notes/mech-interp-safety-alignment-research-map/ 2026-06-21T00:00:00+00:00 /notes/regularization/ 2026-06-21T00:00:00+00:00 /notes/autoencoders/ 2026-06-21T00:00:00+00:00 /notes/the-origins-of-representation-manifolds-in-largelanguage-models/ 2026-06-21T00:00:00+00:00 /notes/everything-everywhere-all-at-once-is-mechanistic-interpretability-identifiable/ 2026-06-22T00:00:00+00:00 /notes/untitled/ 2026-06-22T00:00:00+00:00 /notes/when-language-overwrites-vision-over-alignmentand-geometric-debiasing-in-vision-language-models/ 2026-06-22T00:00:00+00:00 /notes/not-all-language-model-features-are-one-dimensionally-linear/ 2026-06-23T00:00:00+00:00 /notes/the-manifold-turn-in-mechanistic-interpretability-a-review-of-geo-metric-approaches-to-understanding-neural-network-internals/ 2026-06-23T00:00:00+00:00 /notes/mnist-dataset/ 2026-06-28T00:00:00+00:00 /notes/sparse-autoencoder/ 2026-06-28T00:00:00+00:00 /notes/polysemantic/ 2026-06-28T00:00:00+00:00 /notes/sentence-transformers/ 2026-07-04T00:00:00+00:00 /notes/softmax/ 2026-07-05T00:00:00+00:00 /notes/analysing-encoded-concepts-in-transformer-language-models/ 2026-07-06T00:00:00+00:00 /notes/finding-manifolds-with-bilinear-autoencoders/ 2026-07-07T00:00:00+00:00 /notes/liner-representation-hypothesis/ 2026-07-09T00:00:00+00:00 /notes/manifold-hypothesis/ 2026-07-09T00:00:00+00:00 /notes/how-can-ai-help-india/ 2026-07-11T00:00:00+00:00 /notes/manifold-steering-revels-the-shared-geometry-of-neural-network-representation-and-behavior/ 2026-07-12T00:00:00+00:00 /notes/proposal-building-blocks-of-intelligence/ 2026-07-13T00:00:00+00:00 /notes/llm-self-correction-in-vision-language-action-models-via-simulation-driven-optimization/ 2026-07-16T00:00:00+00:00 /notes/paper-outline/ 2026-07-16T00:00:00+00:00 /2019/09/16/building-messenger-in-java/ 2019-09-16T00:00:00+00:00 /2020/04/28/visualization-tool-for-algorithms/ 2020-04-28T00:00:00+00:00 /2021/01/22/serial-pan-number-generator/ 2021-01-22T00:00:00+00:00 /2021/04/14/building-a-simple-multiplayer-game/ 2021-04-14T00:00:00+00:00 /2023/02/07/why-and-why-not-nodejs/ 2023-02-07T00:00:00+00:00 /2025/09/22/datascience-in-supply-chain-logistics/ 2025-09-22T00:00:00+00:00 /about/ / /notes/ /tagged/