Brain-like AGI project “aintelope”
Steven Byrnes called for a brain-like AGI research agenda, and three guys from the Hamburg EA community listened.
We are excited about Steven’s five-star program 15.2.1.2 “Reverse-engineer human social instincts,” and kicked off work a few weeks ago in June. We familiarized ourselves with Steven’s brain-like AGI framework, and meet weekly now.
This post is an announcement and a request for feedback and collaboration.
Why us?
We have a great skill fit:
A professional data scientist with the required machine learning experience to implement RL agents,
A professional Python developer with game-programming background to implement the world mode, and visualization.
A seasoned software engineer with startup CTO experience who takes care of everything else, e.g., this blog post (me).
What have we done so far?
We have already implemented a toy world and simple RL agent in a first iteration of Steven’s framework. We build on top of the Python framework PettingZoo. Our code is in a private Github repo that we believe should stay private given the potential impact. Looking for thoughts on this.
We have collected a list of more than 60 candidate instincts from neuroscience and other sources that we can implement and experiments with.
The project website will be here: https://www.aintelope.net/ (effectively empty right now).
The project and our progress so far were presented at the Human-aligned AI Summer School in Prague on August 5th, where we got feedback about the project, brain-like AGI in general, and found the three participants who wanted to collaborate.
What do we want to do?
Implementing models and running tests is a proven way to test theories and check our understanding of the models. Better quick success/failure on something where it is too easy to build a big theory.
Specifically, we want to:
Show that a relatively simple set of instincts can shape complex behaviors of a single agent.
Show whether the instincts lead to significantly reduced training time compared to agents without such instincts.
Extend the simulation to groups of agents.
Show that prosocial behavior can be shaped with few instincts.
See if we can get Ersatz Interpretability working.
In the ideal case, the simulated agents show behavior consistent with having values like altruism or honesty.
Immediate next steps:
Implement food-related thought-assessors.
Implement different types of social cues to get to collaborative behavior. Probably not the three types suggested by Steven as motivating examples.
How can you help?
Please give us feedback.
Review what we already have (requires an invite, please request).
Help with funding and growth of the project (I am applying to LTFF).
- (My understanding of) What Everyone in Technical Alignment is Doing and Why by Aug 29, 2022, 1:23 AM; 413 points) (
- My AGI safety research—2022 review, ’23 plans by Dec 14, 2022, 3:15 PM; 51 points) (
- Alignment via prosocial brain algorithms by Sep 12, 2022, 1:48 PM; 45 points) (
- What is good Cyber Security Advice? by Oct 24, 2022, 11:27 PM; 30 points) (
- Sep 1, 2022, 10:41 PM; 30 points) 's comment on (My understanding of) What Everyone in Technical Alignment is Doing and Why by (
- EAI Alignment Speaker Series #1: Challenges for Safe & Beneficial Brain-Like Artificial General Intelligence with Steve Byrnes by Mar 23, 2023, 2:32 PM; 28 points) (
- aintelope project update by Feb 8, 2024, 6:32 PM; 24 points) (
- Feb 26, 2023, 1:27 PM; 10 points) 's comment on The Preference Fulfillment Hypothesis by (
- Aug 29, 2022, 9:42 AM; 9 points) 's comment on (My understanding of) What Everyone in Technical Alignment is Doing and Why by (
- Baseline of my opinion on LW topics by Sep 2, 2013, 12:13 PM; 8 points) (
- Dec 1, 2022, 7:05 PM; 7 points) 's comment on johnswentworth’s Shortform by (
- Oct 13, 2022, 8:23 PM; 3 points) 's comment on Niceness is unnatural by (
- Nov 17, 2022, 12:42 AM; 3 points) 's comment on The Alignment Community Is Culturally Broken by (
Good luck!! :)
Excited and happy that you are moving forward with this project. It’s great to know that more paths to alignment are being actively investigated.