Startups | AI | info...ย โขย 7m
the whole system prompt of claude has been leaked on github ๐ 24k tokens long, it defines model behavior, tool use, and citation format. ๐ https://raw.githubusercontent.com/asgeirtj/system_prompts_leaks/refs/heads/main/claude.txt

Founder | Agentic AI...ย โขย 16d
4 different ways of training LLM's. I've given a simple detailed explanation below. 1.) ๐๐ฐ๐ฐ๐๐ฟ๐ฎ๐๐ฒ ๐๐ฎ๐๐ฎ ๐๐๐ฟ๐ฎ๐๐ถ๐ผ๐ป (๐๐๐ฒ๐ฝ-๐ฏ๐-๐๐๐ฒ๐ฝ) Prepares clean, consistent, and useful data so the model learns effectively. 1. Collect text
See More
Download the medial app to read full posts, comements and news.