Get Software Quality Engineering Qualified Today!

Public collection

Helpful, Honest, Harmless

A rabbit hole of the Helpful, Honest, Harmless (HHH) Model for AI.

Rosie Sherry

- 19 items

We Think, Therefore We Align LLMs to Helpful, Harmless and Honest Before They Go Wrong image

We Think, Therefore We Align LLMs to Helpful, Harmless and Honest Before They Go Wrong

‘Helpful, Honest, Harmless’ AI image

‘Helpful, Honest, Harmless’ AI

Too Helpful, Too Harmless, Too Honest or Just Right? image

Too Helpful, Too Harmless, Too Honest or Just Right?

3 Hs for AI: Helpful, Honest, and Harmless image

3 Hs for AI: Helpful, Honest, and Harmless

We need an adaptive interpretation of helpful, honest and harmless principles image

We need an adaptive interpretation of helpful, honest and harmless principles

A Decision Tree for Responsible AI Implementation Using the Harmless - Helpful - Honest Framework image

A Decision Tree for Responsible AI Implementation Using the Harmless - Helpful - Honest Framework

RLHF for harmless, honest, and helpful AI image

RLHF for harmless, honest, and helpful AI

How to train helpful, honest, and harmless AI Learn how to implement a helpful, honest, and harmless model that meets... image

How to train helpful, honest, and harmless AI Learn how to implement a helpful, honest, and harmless model that meets standards through human-generated data in order to meet the needs of users and enterprises.

Prioritization First, Principles Second: An Adaptive Interpretation of Helpful, Honest, and Harmless Principles image

Prioritization First, Principles Second: An Adaptive Interpretation of Helpful, Honest, and Harmless Principles

Honest, Harmless and Helpful Evaluations image

Honest, Harmless and Helpful Evaluations

"Helpful, Harmless, and Honest" image

"Helpful, Harmless, and Honest"

Developing LLMs that are helpful, truthful, and harmless image

Developing LLMs that are helpful, truthful, and harmless

Helpful, harmless, honest? Sociotechnical limits of AI alignment and safety through Reinforcement Learning from Human... image

Helpful, harmless, honest? Sociotechnical limits of AI alignment and safety through Reinforcement Learning from Human Feedback

Helpful, harmless, honest? Sociotechnical limits of AI alignment and safety through Reinforcement Learning from Human... image

Helpful, harmless, honest? Sociotechnical limits of AI alignment and safety through Reinforcement Learning from Human Feedback

Harmless, Honest, and Helpful AI: Aligning AI the Right Way image

Harmless, Honest, and Helpful AI: Aligning AI the Right Way

Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback image

Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reinforcement Learning from Human Feedback: Improving AI with LLM Alignment image

Reinforcement Learning from Human Feedback: Improving AI with LLM Alignment

A General Language Assistant as a Laboratory for Alignment image

A General Language Assistant as a Laboratory for Alignment

Tailoring AI Behavior to Context: Adaptive HHH Alignment image

Tailoring AI Behavior to Context: Adaptive HHH Alignment

Rosie Sherry

CEO & Founder at Ministry of Testing

She/Her

I've been working in the software testing and quality engineering space since the year 2000 whilst also combining it with my love for education and community. It turns out quality, community and education go nicely hand in hand.

🎓 MoT-STEC qualified

Team Account Member

MoTaverse Team

Chapter Lead

More Collections

The Community's Guide to Onboarding image

The Community's Guide to Onboarding

Items to help you and your new hire get started in their new job

26 Nov 24

Community Thoughts image

Community Thoughts

A collection of articles on what the software testing community really thinks about current software testing topics

11 Feb 24

Communities of Practice image

Communities of Practice

A list of resources for building Communities of Practice.

08 Nov 24

Collection FAQs

What are Collections? They are a way to organize our software testing and QA content into an easily shareable format.

Why create Collections? We all want to learn and often share what we are learning, creating a collection helps organise software testing knowledge into a comprehensible way.

What can we add to Collections? At the moment you can add content that is created and hosted on Ministry of Testing.

Who can add collections? Professional Members have the ability to create unlimited collections, privately or publicly.