My LLM Exploration Journey and Current Workflow

摘要

我的 LLM 使用從 Copilot Pro 歷經 Gemini、Perplexity、Claude，現主力為 Gemini Advanced（2.5 Pro）。互動模式從問答演進至深度搜尋。現透過 Gemini Advanced 深度搜尋與整理報告，需視覺化時則用 Claude AI（3.7 Sonnet）產出 HTML，滿足探究需求。

Abstract

My LLM journey spanned Copilot Pro, various Gemini versions, Perplexity, and Claude, now centering on Gemini Advanced (2.5 Pro). Interaction evolved from Q&A to deep search. Currently, I use Gemini Advanced for deep searches and initial reports, turning to Claude AI (3.7 Sonnet) for visualized HTML outputs to satisfy in-depth inquiries.

klo.lt Podcast Player

klo.lt is a podcast player I created to organize my favorite podcasts and streamline my listening experience.

Source code

This project is integrated from the following projects:

• redirect
• CFP2 (backend)
• CFP2-BLG
• CFP2-EXR
• CFP2-JST
• CFP2-ASC

CFP2 and its derivative sub-projects will be discontinued and replaced by klo.lt.

Codename: MediterrFloatingCity revisit

Tool

• Bing AI Image creator: https://www.bing.com/create

Result

• Prompt: A mediterranean city on a island floating in the air. Waterfall is falling up into the sky in the background.

  • Link: https://www.bing.com/images/create/a-mediterranean-city-on-a-island-floating-in-the-a/653f1753c7aa4975aca1c3b725ee11e4

    

Third try 2.0: MaLTHA

為了進一步提高 pyMoTH 的適用性，我修改 pyMoTH 並重新以 MaLTHA 發布於 PyPI 上。不過，我還沒完成 Documentation。