This is a special post for quick takes by Minh Nguyen. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.
Comment Permalink
Suggestion for EAGs/EAGx:
Please give more detail on your Swapcard about your research/projects. Even just the title of the research paper, or any links.
I always review the entire attendee list. I actively want to meet people, but if someone just puts "I am trying to get into AI alignment research", I literally have nothing to go off, and can't think of a reason to reach out with so few details.
This also saves time during 1-on-1s so you don't re-introduce yourself/areas of interest every 30 minutes.
If you don't have a project/experience, you can even put ideas you're fascinated by, or groups you identify with. I literally Ctrl+F "ADHD", "startup", "Singapore" and other keywords related to my research interests.
Hello! I'm looking for AI Safety proposals/project ideas to deploy within CivitAI, the biggest open-source AI image model hosting platform.
I own AI Hub, an AI voice model hosting platform w/ ~1 million users. We are discussing integration/merging with CivitAI.com, which is an open source AI model hosting platform and the 7th most visited AI website with 27 million monthly users. Most of their hosting is Stable Diffusion image models, but I'm helping them introduce AI voice cloning model hosting. I'd get a lot of autonomy over distribution for voice and possibly text models.
The founders mentioned they’re also exploring content moderation solutions, and when I asked, they said they were open to working with AI Safety companies. CivitAI is very influential in the open-source community, so I think shaping policy here could significantly shape AI Safety wrt open-source and local models. Some directions I’m exploring:
- Content and open source model moderation frameworks/tools
- Collecting data and running tests that aid alignment research
If anyone has ideas, or knows anyone who might be interested, do LMK! This is exploratory, but I aim to formulate an idea and deploy to users within ~3 months, with 80% confidence. I am literally open to trying any suggestions - for-profit, nonprofit, research, product, governance, alignment research etc.
Even if you have an idea that’s not AI image-related, I have a decent (40%) chance of proposing it to Github, Huggingface etc. Plus, my task is to diversify outside of image models anyway, so LLM-related proposals could still be relevant.
(this is still in exploratory/idea phase, and I wasn't sure if this should be a full post)
In AI Safety, it seems easy to feel alienated and demoralised.
The stakes feel vaguely existential, most normal people have no opinion on it, and it never quite feels like "saving a life". Donating to global health or animal welfare feel more direct, if still distant.
I would imagine a young software developer discovers EA, and then AI Safety, hoping to do something meaningful. But the moments after that, feel much the same as it would a normal job.
Curious if others feel the same.
Curated and popular this week
·
Note: I am not a malaria expert. This is my best-faith attempt at answering a question that was bothering me, but this field is a large and complex field, and I’ve almost certainly misunderstood something somewhere along the way.
Summary
While the world made incredible progress in reducing malaria cases from 2000 to 2015, the past 10 years have seen malaria cases stop declining and start rising. I investigated potential reasons behind this increase through reading the existing literature and looking at publicly available data, and I identified three key factors explaining the rise:
1. Population Growth: Africa's population has increased by approximately 75% since 2000. This alone explains most of the increase in absolute case numbers, while cases per capita have remained relatively flat since 2015.
2. Stagnant Funding: After rapid growth starting in 2000, funding for malaria prevention plateaued around 2010.
3. Insecticide Resistance: Mosquitoes have become increasingly resistant to the insecticides used in bednets over the past 20 years. This has made older models of bednets less effective, although they still have some effect. Newer models of bednets developed in response to insecticide resistance are more effective but still not widely deployed.
I very crudely estimate that without any of these factors, there would be 55% fewer malaria cases in the world than what we see today. I think all three of these factors are roughly equally important in explaining the difference.
Alternative explanations like removal of PFAS, climate change, or invasive mosquito species don't appear to be major contributors.
Overall this investigation made me more convinced that bednets are an effective global health intervention.
Introduction
In 2015, malaria rates were down, and EAs were celebrating. Giving What We Can posted this incredible gif showing the decrease in malaria cases across Africa since 2000:
Giving What We Can said that
> The reduction in malaria has be
·
"Part one of our challenge is to solve the technical alignment problem, and that’s what everybody focuses on, but part two is: to whose values do you align the system once you’re capable of doing that, and that may turn out to be an even harder problem", Sam Altman, OpenAI CEO (Link).
In this post, I argue that:
1. "To whose values do you align the system" is a critically neglected space I termed “Moral Alignment.” Only a few organizations work for non-humans in this field, with a total budget of 4-5 million USD (not accounting for academic work). The scale of this space couldn’t be any bigger - the intersection between the most revolutionary technology ever and all sentient beings. While tractability remains uncertain, there is some promising positive evidence (See “The Tractability Open Question” section).
2. Given the first point, our movement must attract more resources, talent, and funding to address it. The goal is to value align AI with caring about all sentient beings: humans, animals, and potential future digital minds. In other words, I argue we should invest much more in promoting a sentient-centric AI.
The problem
What is Moral Alignment?
AI alignment focuses on ensuring AI systems act according to human intentions, emphasizing controllability and corrigibility (adaptability to changing human preferences). However, traditional alignment often ignores the ethical implications for all sentient beings. Moral Alignment, as part of the broader AI alignment and AI safety spaces, is a field focused on the values we aim to instill in AI. I argue that our goal should be to ensure AI is a positive force for all sentient beings.
Currently, as far as I know, no overarching organization, terms, or community unifies Moral Alignment (MA) as a field with a clear umbrella identity. While specific groups focus individually on animals, humans, or digital minds, such as AI for Animals, which does excellent community-building work around AI and animal welfare while
Suggestion for EAGs/EAGx:
Please give more detail on your Swapcard about your research/projects. Even just the title of the research paper, or any links.
I always review the entire attendee list. I actively want to meet people, but if someone just puts "I am trying to get into AI alignment research", I literally have nothing to go off, and can't think of a reason to reach out with so few details.
This also saves time during 1-on-1s so you don't re-introduce yourself/areas of interest every 30 minutes.
If you don't have a project/experience, you can even put ideas you're fascinated by, or groups you identify with. I literally Ctrl+F "ADHD", "startup", "Singapore" and other keywords related to my research interests.
That's a great comment.
In general I would have like to have seen 30-50% more info on people's swapcards, but I know there is a tradeoff in effort and readability there as well. Like you say projects and specific interests can be super useful.