Institute for Meaning Alignment
Subscribe
Sign in
Home
Archive
Leaderboard
About
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
•
Joe Edelman
and
Oliver Klingefjord
11
Share this post
Introducing Democratic Fine-Tuning
meaningalignment.substack.com
Copy link
Facebook
Email
Notes
Other
1
New
Help us make ChatGPT wiser
Join our OpenAI-backed experiment to democratically fine-tune ChatGPT's values.
Sep 20
•
Joe Edelman
and
Oliver Klingefjord
4
Share this post
Help us make ChatGPT wiser
meaningalignment.substack.com
Copy link
Facebook
Email
Notes
Other
6
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
•
Joe Edelman
8
Share this post
We are now "The Institute for Meaning Alignment"
meaningalignment.substack.com
Copy link
Facebook
Email
Notes
Other
Institute for Meaning Alignment
Updates from the frontier or AI, flourishing, and new institutions.
Subscribe
Us
Institute for Meaning Alignment
Our discord
Institute for Meaning Alignment
Subscribe
About
Archive
Sitemap
Share this publication
Institute for Meaning Alignment
meaningalignment.substack.com
Copy link
Facebook
Email
Notes
Other
Institute for Meaning Alignment
Updates from the frontier or AI, flourishing, and new institutions.
Launched 2 years ago
Subscribe
No thanks
By registering you agree to Substack's
Terms of Service
, our
Privacy Policy
, and our
Information Collection Notice
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
