Hi Everyone, We'll be starting an informal cohort on AI Safety Fundamentals. Come join-us on Discord. We'll do a poll next week to find a slot that works for most people. (if you're interested in participating as an expert, do reach out as well) We'll do the kick-off session on...
Hello Everyone, Next Tuesday, the US Senate will hold a hearing on AI (https://www.judiciary.senate.gov/committee-activity/hearings/oversight-of-ai-rules-for-artificial-intelligence). OpenAI CEO Sam Altman will testify before Congress for the first time. We believe this is a great opportunity to bring awareness to some of the risks posed by AI technologies, and build common knowledge among...
I’m grateful to Michaël Trazzi. We had a great discussion on this topic, and he then was kind enough to proofread the draft of this article. Abstract Substrate-independence of mental states proves too much, so it is not necessarily true. The consequence is that simulations of conscious beings are not...
For any piece of information (expert statements, benchmarks, surveys, etc.) most good faith people agree on wether it makes doom more or less likely.
But we don't agree on how much they should move our estimates, and there's no good way of discussing that.
How to do better?
Hi Everyone,
We'll be starting an informal cohort on AI Safety Fundamentals.
Come join-us on Discord. We'll do a poll next week to find a slot that works for most people. (if you're interested in participating as an expert, do reach out as well)
We'll do the kick-off session on the 17th of June, and then do the course at the pace of one session per week for eight weeks (you'll be able to discuss the material in-between with other members). I'm currently reaching out to aligment researchers interested in popping in for insights and answering questions we might have.
We'll then do the AI Governance course (https://aisafetyfundamentals.com/ai-governance-curriculum), and then the AI Alignment 201 course (https://aisafetyfundamentals.com/alignment-201-curriculum) - you should be able to singlehandedly solve AGI by the end.
Please note that this is not an official cohort, there is one starting on governance this summer (you can join on AI Safety Fundamentals' website), and one on AI Alignement in September (registrations not opened yet).
Bye!
Tiago
Certainly a thought provoking post! We try to think about the downsides of polarization and how to avoid them.
In this precise case do you think it's a risk?
Hello Everyone,
Next Tuesday, the US Senate will hold a hearing on AI (https://www.judiciary.senate.gov/committee-activity/hearings/oversight-of-ai-rules-for-artificial-intelligence). OpenAI CEO Sam Altman will testify before Congress for the first time.
We believe this is a great opportunity to bring awareness to some of the risks posed by AI technologies, and build common knowledge among US policymakers on possible solutions.
If you live in the United States, you can play an important role as a constituent. Please reach out to your senator who will be present at this hearing, and voice your concerns about AI safety. To help them navigate the debate, we propose a list of questions, initially drafted by Siméon to share with the senators present at the... (read more)
Thanks ! I uploaded the images to https://imgbb.com/ and uploaded them here from there.
I’m grateful to Michaël Trazzi. We had a great discussion on this topic, and he then was kind enough to proofread the draft of this article.
Abstract
Substrate-independence of mental states proves too much, so it is not necessarily true. The consequence is that simulations of conscious beings are not necessarily conscious themselves.
A simulation is only a means for an observer to see the development of a system over time, not the creation of that system. Hence, changing the simulation has no influence on the simulated system.
I - Introduction and definitions
The simulation hypothesis is not only widespread in philosophy, it has also found its way in pop-culture. The best known version of this... (read 1406 more words →)
Thanks for your post, I appreciate the improvement to your argument !
1- It isn't clear to me why observing other forms of conscious intelligences leads to low interest in running non-me-simulations and only non-me-simulations. To me, there are other reasons to make simulations than those you highlited. I might concede that observing other forms of conscious intelligence might lessen motivation for creating full-scale simulations, but I think it would also reduce the need for me-simulations, for the same reasons.
2- Since there is a non-zero chance for you to be in an non-me-simulation or in reality, wouldn't it still compell you to act altruistically, at least to some extent ? What are the probabilities you would assign to those events ?
Thanks for doing these, you have a rare gift
I look forward to your posts on AI every week!