Takumi Matsunobu tkmim

Local LLM as a private writing assistant (This post is written as of August 2024.) I just leave some notes for my experiment of setting up a local LLM that helps to improve my writing by giving internal peer-review. Though the outcome was not satisfying in my case, it showed some potentials to be usable in the not-far future. Conditions and goals Full text is already written in English. It should be understandable, but contains grammatical errors and could be largely improved.

Schafkopf Farbe im Karten Eichel (Kreuz, EN: Club) Gras (Pik, EN: Spade) Herz (EN: Heart) Schellen (Karo, EN:Diamond) die Reihenfolge das Ass die stärkste Karte ist, dann kommt die 10, der König, Dame/Ober, Bube/Unter, 9, 8 und die 7. Reference ()[https://www.sauspiel.de/schafkopf-lernen/das-schafkopf-blatt]

Setting up latexdiff for trackging changes with citations latexdiffcite is a python wrapper of latexdiff, which makes a track-change tex between given two tex documents taking changes in citations into account. Source https://github.com/twilsonco/latexdiffcite https://pypi.org/project/latexdiffcite/ Instalattion Since latexdiffcite is a simple wrapper of latexdiff, the prerequirement is of course latexdiff already installed. Upon that, the easiest way to install latexdiffcite is just using pip like: pip install latexdiffcite Usage If successfully installed, the one liner below immediately produces diff.

1. はじめに xxxx x. Markdown CheetSheet Text Format Italic（斜体） Italic（斜体） Emphasis（強調） Emphasis（強調） Strikethrough（取

元祖 github-style からの変更履歴 アイコンを日替わりの identicon に設定 (6 March 2022) Publication への固定リンクをメニューに追加 (layout/partials/menu.html) (6 March 2022) ライトモード・ダークモードの切り替えトグルアイ

In preparation/Submitted Matsunobu, T., Keil, C. and Craig, C. G. (2025) A Variance Budget to estimate the Growth and Interaction of Uncertainties in Convective-scale Forecasts. Submitted. Peer-reviewed articles Tintó Prims, O., Redl, R., Rautenhaus, M., Selz, T., Matsunobu, T., Modali, K. R., and Craig, G. (2024) The effect of lossy compression of numerical weather prediction data on data analysis: a case study using enstools-compression 2023.11, Geosci. Model Dev., 17, 8909–8925, https://doi.