Back

Kimiko

Startups | AI | info... • 10m

the whole system prompt of claude has been leaked on github šŸ‘€ 24k tokens long, it defines model behavior, tool use, and citation format. šŸ”— https://raw.githubusercontent.com/asgeirtj/system_prompts_leaks/refs/heads/main/claude.txt

2 Replies
7
18
Replies (2)

More like this

Recommendations from Medial

Image Description

Rahul Agarwal

Founder | Agentic AI... • 3m

4 different ways of training LLM's. I've given a simple detailed explanation below. 1.) š—”š—°š—°š˜‚š—æš—®š˜š—² š——š—®š˜š—® š—–š˜‚š—æš—®š˜š—¶š—¼š—» (š˜€š˜š—²š—½-š—Æš˜†-š˜€š˜š—²š—½) Prepares clean, consistent, and useful data so the model learns effectively. 1. Collect text

See More
Reply
1
9
1

Download the medial app to read full posts, comements and news.