Archive - Meaning Alignment Institute

[New paper] 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 •

,

Oliver Klingefjord

, and

February 2024

David Shapiro Interview

And two other quick updates;

Feb 6 •

Oliver Klingefjord

and

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 •

Meaning Alignment Institute: Year in Review

And what's next for 2024

Dec 29, 2023 •

Oliver Klingefjord

and

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 •

and

Oliver Klingefjord

September 2023

Help us make ChatGPT wiser

Join our OpenAI-backed experiment to democratically fine-tune ChatGPT's values.

Sep 20, 2023 •

and

Oliver Klingefjord

August 2023

We are now "The Institute for Meaning Alignment"

Hello everyone! Many of you found us first through the talks we released last January, under the name “Rebuilding Meaning”.Institute for Meaning…

Aug 29, 2023 •

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 •

and

Oliver Klingefjord

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts