Effective Altruism Forum
EA Forum

Hide table of contents
by Per Ivar Friborg
1 min read 1

35

AI safetyStudent projectsAI alignment
Frontpage

Anyone can undertake this project, and feel free to make use of the complete project description with all details needed to undertake this project individually or as a facilitator. Message plex#1874 on Discord after adding him as a friend for invites to Robert Miles' AI Discord, and to receive an onboarding call if you want to run a similar project.

Short description

Robert Miles is a successful YouTuber making AI Safety related content. Robert Miles’ AI Discord community is working on an interactive FAQ as a single point of entry into alignment (WIP prototype), and the wiki which stores questions and answers is ready to be used. Participants would write and organize questions and answers on Stampy’s Wiki, and give feedback on the software. This project is fit for students looking for ways to contribute to AI alignment and getting involved while learning.

Evaluation

The first iteration of this project has recently been tested by 4 members of EA NTNU, all of them being students, working 3 hours weekly for 6 weeks. EA NTNU is an engagement driven local group at the Norwegian University of Science and Technology (NTNU). This was done as part of the weekly work sessions facilitated by EA NTNU, where all members of EA NTNU gather physically to work with separate projects. The evaluation revealed great results with members reporting that this way of learning about AI alignment in a meaningful context was more engaging, and thus more effective, given that the increased engagement made them invest more in the learning process. All members were very new to AI in general, making it reasonable to believe that anyone can undertake this project as long as they are willing to learn.

Our project group focused only on answering questions on Stampy's Wiki, however, other groups may consider contributing to the development of Stampy as well. Here is a list of answers the group wrote for those that are curious: EA NTNU - Stampy's Wiki. Additionally, the developers were inspired to make new features on seeing how people actually used the system. 

Major thanks to plex for feedback on this post, and for helping out with the project description.

35

0
0

Reactions

0
0
Mentioned in
Comments1


Sorted by
New & upvoted
Click to highlight new comments since:
NunoSempere3
0
0

Looks cool!

Reply
More from Per Ivar Friborg
42
Data Taxation: A Proposal for Slowing Down AGI Progress
Per Ivar Friborg
· · 15m read
6
6
51
How to Incubate Self-Driven Individuals (for Leaders and Community Builders)
Per Ivar Friborg
· · 8m read
4
4
View more
Curated and popular this week
 ·  · 38m read
 · 
In recent months, the CEOs of leading AI companies have grown increasingly confident about rapid progress: * OpenAI's Sam Altman: Shifted from saying in November "the rate of progress continues" to declaring in January "we are now confident we know how to build AGI" * Anthropic's Dario Amodei: Stated in January "I'm more confident than I've ever been that we're close to powerful capabilities... in the next 2-3 years" * Google DeepMind's Demis Hassabis: Changed from "as soon as 10 years" in autumn to "probably three to five years away" by January. What explains the shift? Is it just hype? Or could we really have Artificial General Intelligence (AGI)[1] by 2028? In this article, I look at what's driven recent progress, estimate how far those drivers can continue, and explain why they're likely to continue for at least four more years. In particular, while in 2024 progress in LLM chatbots seemed to slow, a new approach started to work: teaching the models to reason using reinforcement learning. In just a year, this let them surpass human PhDs at answering difficult scientific reasoning questions, and achieve expert-level performance on one-hour coding tasks. We don't know how capable AGI will become, but extrapolating the recent rate of progress suggests that, by 2028, we could reach AI models with beyond-human reasoning abilities, expert-level knowledge in every domain, and that can autonomously complete multi-week projects, and progress would likely continue from there.  On this set of software engineering & computer use tasks, in 2020 AI was only able to do tasks that would typically take a human expert a couple of seconds. By 2024, that had risen to almost an hour. If the trend continues, by 2028 it'll reach several weeks.  No longer mere chatbots, these 'agent' models might soon satisfy many people's definitions of AGI — roughly, AI systems that match human performance at most knowledge work (see definition in footnote). This means that, while the compa
 ·  · 4m read
 · 
SUMMARY:  ALLFED is launching an emergency appeal on the EA Forum due to a serious funding shortfall. Without new support, ALLFED will be forced to cut half our budget in the coming months, drastically reducing our capacity to help build global food system resilience for catastrophic scenarios like nuclear winter, a severe pandemic, or infrastructure breakdown. ALLFED is seeking $800,000 over the course of 2025 to sustain its team, continue policy-relevant research, and move forward with pilot projects that could save lives in a catastrophe. As funding priorities shift toward AI safety, we believe resilient food solutions remain a highly cost-effective way to protect the future. If you’re able to support or share this appeal, please visit allfed.info/donate. Donate to ALLFED FULL ARTICLE: I (David Denkenberger) am writing alongside two of my team-mates, as ALLFED’s co-founder, to ask for your support. This is the first time in Alliance to Feed the Earth in Disaster’s (ALLFED’s) 8 year existence that we have reached out on the EA Forum with a direct funding appeal outside of Marginal Funding Week/our annual updates. I am doing so because ALLFED’s funding situation is serious, and because so much of ALLFED’s progress to date has been made possible through the support, feedback, and collaboration of the EA community.  Read our funding appeal At ALLFED, we are deeply grateful to all our supporters, including the Survival and Flourishing Fund, which has provided the majority of our funding for years. At the end of 2024, we learned we would be receiving far less support than expected due to a shift in SFF’s strategic priorities toward AI safety. Without additional funding, ALLFED will need to shrink. I believe the marginal cost effectiveness for improving the future and saving lives of resilience is competitive with AI Safety, even if timelines are short, because of potential AI-induced catastrophes. That is why we are asking people to donate to this emergency appeal
 ·  · 1m read
 · 
We’ve written a new report on the threat of AI-enabled coups.  I think this is a very serious risk – comparable in importance to AI takeover but much more neglected.  In fact, AI-enabled coups and AI takeover have pretty similar threat models. To see this, here’s a very basic threat model for AI takeover: 1. Humanity develops superhuman AI 2. Superhuman AI is misaligned and power-seeking 3. Superhuman AI seizes power for itself And now here’s a closely analogous threat model for AI-enabled coups: 1. Humanity develops superhuman AI 2. Superhuman AI is controlled by a small group 3. Superhuman AI seizes power for the small group While the report focuses on the risk that someone seizes power over a country, I think that similar dynamics could allow someone to take over the world. In fact, if someone wanted to take over the world, their best strategy might well be to first stage an AI-enabled coup in the United States (or whichever country leads on superhuman AI), and then go from there to world domination. A single person taking over the world would be really bad. I’ve previously argued that it might even be worse than AI takeover. [1] The concrete threat models for AI-enabled coups that we discuss largely translate like-for-like over to the risk of AI takeover.[2] Similarly, there’s a lot of overlap in the mitigations that help with AI-enabled coups and AI takeover risk — e.g. alignment audits to ensure no human has made AI secretly loyal to them, transparency about AI capabilities, monitoring AI activities for suspicious behaviour, and infosecurity to prevent insiders from tampering with training.  If the world won't slow down AI development based on AI takeover risk (e.g. because there’s isn’t strong evidence for misalignment), then advocating for a slow down based on the risk of AI-enabled coups might be more convincing and achieve many of the same goals.  I really want to encourage readers — especially those at labs or governments — to do something
Recent opportunities in AI safety
33
Contracting Opportunity: Be a shortform video editor for the new 80,000 Hours Video Program (even if you haven't edited before!)
2 authors
· · 2m read
0
0
15
Open call: "Existential risk of AI: technical conditions"
miller-max
· · 1m read
0
0
23
Creating 'Making God': a Feature Documentary on risks from AGI
ConnorA
· · 9m read
8
8
View more