The 8-Word Prompt That’s Revolutionizing AI Creativity 🚀
Last Updated on November 6, 2025 by Editorial Team
Author(s): MahendraMedapati
Originally published on Towards AI.
How Stanford Researchers Unlocked 2× More Diverse AI Outputs Without Retraining a Single Model
Have you ever asked ChatGPT to write you five different jokes about the same topic, only to get the same punchline over and over again? Or requested creative ideas and received disappointingly similar responses?
The article discusses a groundbreaking method called “Verbalized Sampling” developed by a Stanford research team, which significantly increases the diversity of AI-generated outputs without needing major retraining of AI models. This technique, which involves asking AI to generate multiple responses with associated probabilities, allows models to explore their full range of creativity rather than defaulting to safe, typical responses. The findings suggest that the creativity within AI models was always present but underutilized due to the conventional methods of interaction.
Read the full blog for free on Medium.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.
Published via Towards AI
Towards AI Academy
We Build Enterprise-Grade AI. We'll Teach You to Master It Too.
15 engineers. 100,000+ students. Towards AI Academy teaches what actually survives production.
Start free — no commitment:
→ 6-Day Agentic AI Engineering Email Guide — one practical lesson per day
→ Agents Architecture Cheatsheet — 3 years of architecture decisions in 6 pages
Our courses:
→ AI Engineering Certification — 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course out there.
→ Agent Engineering Course — Hands on with production agent architectures, memory, routing, and eval frameworks — built from real enterprise engagements.
→ AI for Work — Understand, evaluate, and apply AI for complex work tasks.
Note: Article content contains the views of the contributing authors and not Towards AI.
Related posts
Recent Posts
