(づ•ᴥ•)づ┬─┬

Notes on math and machine learning.

28 May, 2026 Paper notes: The implicit dynamics of in-context learning
15 May, 2026 Targeting the gradient flow
05 May, 2026 Lifting gradient flows
28 Apr, 2026 When Trajectories Converge to a Curve
31 Mar, 2026 Matrix Calculus (for ML and beyond) -- notes.
25 Mar, 2026 Solving the inverse problem to find a hidden object
25 Feb, 2026 Greedy Coordinate Gradient
08 Feb, 2026 Compact transformers can't learn all sequences.
10 Jan, 2026 Translating stories to games with language models
30 Dec, 2025 Scale and Direction: Understanding Homogeneous Functions
22 Dec, 2025 Model Merging and the Geometry of Optimization
09 Dec, 2025 Some Linear Algebra from Lewis Signaling Games
09 Nov, 2025 “Reasoning with Sampling” — Notes on Karan & Du (2025)
06 Nov, 2025 A few notes on directed information
01 Oct, 2025 Fun with stochastic activations
05 Sep, 2025 Trying out the GEPA prompt optimizer with chess puzzles
21 Aug, 2025 Adding Facts and Watching LLMs Snap to Rationality
05 Aug, 2025 horizon-alpha and horizon-beta also betting, gpt-oss-20B is thinking first.
30 Jul, 2025 Directed graphs from papers with OpenAI o3
26 Jul, 2025 Using ChatGPT Agent to find a coffee carafe with a particular diameter
24 Jul, 2025 Heuristics when LLMs play a betting game
09 Jul, 2025 Turns out general agents contain world models.
03 Jul, 2025 Revisiting a Root-Finding Idea from Undergrad
30 Jun, 2025 LLM agents and chess puzzles
25 May, 2025 Further adventures with LLM curve-guessing
23 Apr, 2025 GPT-2's Anisotropic Antics
17 Apr, 2025 LLMs and Dynamic Cheatsheets: Learning from Experience
02 Apr, 2025 The Smallest Weight Punches Above Its Weight (in Expectation)
23 Mar, 2025 A brief analysis of automerger data, feat. SLERP and DARE-TIES LLM merging
26 Jun, 2024 Yet another self-attention tutorial
20 Jan, 2020 Rewriting the Kullback-Leibler with an integral transform