LESSWRONG
LW

54
Wikitags

AI Safety Mentors and Mentees Program

Edited by Magdalena Wache last updated 10th May 2023

The AI Safety Mentors and Mentees program aims to facilitate mentoring in AI safety. It does so by

  • helping mentees to find mentors (matchmaking)
  • giving some structure to the mentor-mentee relationship
Subscribe
Discussion
Subscribe
Discussion
Posts tagged AI Safety Mentors and Mentees Program
62Announcing AI safety Mentors and Mentees
Ω
Marius Hobbhahn
3y
Ω
7
166What Discovering Latent Knowledge Did and Did Not Find
Ω
Fabien Roger
3y
Ω
17
142The Translucent Thoughts Hypotheses and Their Implications
Ω
Fabien Roger
3y
Ω
7
34[Hebbian Natural Abstractions] Introduction
Samuel Nellessen, Jan
3y
3
29If Wentworth is right about natural abstractions, it would be bad for alignment
Wuschel Schulz
3y
5
28Research Adenda: Modelling Trajectories of Language Models
NickyP
2y
0
27How Do Induction Heads Actually Work in Transformers With Finite Capacity?
Fabien Roger
3y
0
15[Hebbian Natural Abstractions] Mathematical Foundations
Samuel Nellessen, Jan
3y
2
12The Inter-Agent Facet of AI Alignment
Ω
Michael Oesterle
3y
Ω
1
12I made an AI safety fellowship. What I wish I knew.
Ruben Castaing
1y
0
11Launching Applications for the Global AI Safety Fellowship 2025!
Aditya_SK
11mo
5
Add Posts