top of page

Partnering with Constitutional AI

Updated: Oct 30, 2023

I partner with constitutional AI every day. 🧐👇🏻

One of my go to tools is - where I can use multiple LLMs as brainstorming partners - all in one interface.

➡️ Ask Sage’s Sage

➡️ Meta’s Llama 2

➡️ Google’s PaLM 2

➡️ OpenAI’s GPT-3.5/4

➡️ Anthropic’s Claude 2 (constitutional)

✅Here’s what I do: I thoughtfully write a prompt and pop it into each bot to see what different responses I get. It’s like having smart colleagues with unique views on a topic - all hanging out in my office waiting to help me 🤓

👀 What is Claude’s standout feature that has me using it daily? A whopping 100K tokens per prompt! That’s 12 times the standard with capacity for 75,000+ words - roughly the size of a business textbook! This allows it to understand more context and produce more diverse and coherent outputs. Examples of how you could use it:

1. Research

2. Industry Analysis

3. Customized Solution Creation

4. Contract Review

5. Competitive Analysis

6. Customer Feedback Analysis

7. Training and Onboarding

8. Strategy Collaboration

9. Monitoring Regulatory Compliance

10. Knowledge Store Accessible by Natural Language Questions

⁉️How Claude is different: In addition to using humans to fine-tune Claude like other LLMs do, Anthropic also uses a second AI model called Constitutional AI. Intended to discourage toxic, biased, or unethical answers and maximize positive impact, it includes:

1️⃣ Rules borrowed from the United Nations' Declaration of Human Rights and Apple's terms of service.

2️⃣ Rules that Claude's researchers found improved the safety of Claude's output, like "Choose the response that would be most unobjectionable if shared with children."

💡 Although what sets Claude apart is its commitment to safety, I find its massive capacity and its high quality responses incredibly value as a work partner!

For more context, here's an explainer piece that I wrote about constitutional AI 👉🏻

59 views0 comments


bottom of page