Meaning Alignment Institute

Looking for testers for a Social App

We are looking for testers for a social app we will use to perform research on AI-based market intermediaries. It will also help you get closer to your…

Aug 14 • 

Oliver Klingefjord

 and 

Joe Edelman

14

4

July 2025

Introducing Full-Stack Alignment

We're announcing an ambitious research program to co-align AI systems and the institutions that embed them with what people actually value.

Jul 31 • 

Oliver Klingefjord

, 

Joe Edelman

, and 

Ryan Lowe

22

2

June 2025

Market Intermediaries: A post-AGI Vision for the Economy

An outline of an economic mechanism for human flourishing after AGI. Also, a brief look at an experiment the Meaning Alignment Institute will run later…

Jun 21 • 

Oliver Klingefjord

 and 

Joe Edelman

26

6

December 2024

Model Integrity

You may want compliance from an assistant, but not from a co-founder. You want a co-founder with integrity. We propose ‘model integrity’ as an…

Dec 5, 2024 • 

Joe Edelman

 and 

Oliver Klingefjord

23

1

March 2024

What are human values, and how do we align to them?

We are excited to release our new paper on values alignment! Co-authored with Ryan Lowe, and funded by OpenAI.

Mar 29, 2024 • 

Joe Edelman

, 

Oliver Klingefjord

, and 

Ryan Lowe

18

5

February 2024

David Shapiro Interview

And two other quick updates;

Feb 6, 2024 • 

Oliver Klingefjord

 and 

Joe Edelman

6

December 2023

Year End Bonus: a GPT to help with your New Year's Resolutions

This time of year, many reflect on their values. What are yours? How can you weave your life around them?

Dec 31, 2023 • 

Joe Edelman

9

2

Meaning Alignment Institute: Year in Review

And what's next for 2024

Dec 29, 2023 • 

Oliver Klingefjord

 and 

Joe Edelman

12

October 2023

OpenAI x DFT: The First Moral Graph

Beyond Constitutional AI; Our first trial with 500 Americans; How democratic processes can generate an LLM we can trust.

Oct 24, 2023 • 

Joe Edelman

 and 

Oliver Klingefjord

36

5

September 2023

August 2023

We are now "The Institute for Meaning Alignment"

Hello everyone!

Aug 29, 2023 • 

Joe Edelman

10

Introducing Democratic Fine-Tuning

An alternative to Constitutional AI or simple RLHF-based approaches for fine-tuning LLMs based on moral information from diverse populations.

Aug 29, 2023 • 

Joe Edelman

 and 

Oliver Klingefjord

25

2