The Logistics of Distribution of Meaning — AI Alignment Forum

The Logistics of Distribution of Meaning — AI Alignment Forum
This is an excerpt from the Introductions section to a book-length project that was kicked off as a response to ...
Read more

What’s next for reproductive rights in the US

What’s next for reproductive rights in the US
Two years ago, the US Supreme Court overturned Roe v. Wade, a legal decision that protected the right to abortion. ...
Read more

a case study on the refusal direction — AI Alignment Forum

a case study on the refusal direction — AI Alignment Forum
This is an interim report sharing preliminary results. We hope this update will be useful to related research occurring in ...
Read more

Trump’s win is a tragic loss for climate progress

Trump’s win is a tragic loss for climate progress
The US election could create global ripples as well, and very soon. US negotiators will meet with their counterparts at ...
Read more

The US is about to make a sharp turn on climate policy

The US is about to make a sharp turn on climate policy
What, exactly, Trump can do will depend on whether Republicans take control of both houses of Congress. A clean sweep ...
Read more

The Download: inside animals’ minds, and how to make AI agents useful

The Download: inside animals’ minds, and how to make AI agents useful
Studying the minds of other animals comes with a challenge that human psychologists don’t usually face: Your subjects can’t tell ...
Read more

Data Poisoning & Jailbreak-Tuning — AI Alignment Forum

Data Poisoning & Jailbreak-Tuning — AI Alignment Forum
Imagine your once reliable, trusty AI assistant suddenly suggesting dangerous actions or spreading misinformation. This is a growing threat as ...
Read more

The Download: CRISPR’s climate promises, and protecting forests with tech

The Download: CRISPR’s climate promises, and protecting forests with tech
Jennifer Doudna, one of the inventors of the breakthrough gene-editing tool CRISPR, says the technology will help the world grapple ...
Read more

The Compendium, A full argument about extinction risk from AGI — AI Alignment Forum

The Compendium, A full argument about extinction risk from AGI — AI Alignment Forum
We (Connor Leahy, Gabriel Alfour, Chris Scammell, Andrea Miotti, Adam Shimi) have just published The Compendium, which brings together in a ...
Read more

Complete Feedback — AI Alignment Forum

The Compendium, A full argument about extinction risk from AGI — AI Alignment Forum
A simple, weak notion of corrigibility is having a “complete” feedback interface. In logical induction terms, I mean the AI ...
Read more