Hide table of contents

Hey! This is another update from the distillers at the AI Safety Info website (and its more playful clone Stampy).

Here are a couple of the answers that we wrote up over the last month (May 2023). As always let us know in the comments if there are any questions that you guys have that you would like to see answered. 

The list below redirects to individual links, and the collective URL above renders all of the answers in the list on one page at once.

 

How can I help tree

There are many different types of individuals from all manner of different backgrounds who want to contribute to AI Safety. So we added a FAQ with advice on various different ways to help with AI safety.

Here is the unified link for all the answers in the how can I help tree if you wish to navigate to aisafety.info directly. See Steven's post for the full list of individual questions and details.

Other Distillations

 

Developer Updates

There are also a couple of cool new features that the developers of the website worked on. We now have a tags page, which allows the reader to navigate the answers based on the tag that they are most interested in. There is also an implementation of a glossary function which auto-creates a short definition popup whenever a jargony term pops up in the answer that the reader might not be familiar with. Here is a sample answer that shows how this functionality works. Try hovering over the "agent", "s-risk", "Goodhart" etc... links.

This is all still a work in progress, but it is exciting to share everything that the people who are all part of the Stampy project have been working on.

 

Cross-posted to Lesswrong: https://www.lesswrong.com/posts/fFtkQCasMjeEpMdhp/stampy-s-ai-safety-info-new-distillations-3-may-2023

10

0
0

Reactions

0
0
Comments2


Sorted by Click to highlight new comments since:

I always get confused about the difference between superposition and poly-semanticy. Would be great if the article clarified this.

It's always hard finding a balance between brevity + de-jargonification in the answers while also touching on every topic that people might be confused about. Mainly because we expect a large diversity of people with varying technical and non-technical backgrounds to interact with the answers. This means that we try and minimize the information per answer to the main essentials required for understanding the topic.

All that being said, I also don't really know if there is a major difference between polysemanticity and superposition. Additionally, I am also confused about if polysemantic and monosemantic neurons refer to the same underlying concept as disentangled vs distributed representations because all these concepts sound like they are describing the same thing. I took note of your comment in the thread about that particular answer, and will get back to it when I learn more.

If you have any resources/posts/papers that point out that they are indeed different let me know and I'll write up a new answer. Something like - What is the difference between polysemantic neurons and superposition?, and, What is the difference between solving polysemanticity in neurons and disentangling latent space representations?

Alternatively, if you come by some awesome explanation and feel like writing it up, you could just edit the stampy docs on superposition or polysemanticity yourself.

More from markov
49
· · 4m read
Curated and popular this week
abrahamrowe
 ·  · 9m read
 · 
This is a Draft Amnesty Week draft. It may not be polished, up to my usual standards, fully thought through, or fully fact-checked.  Commenting and feedback guidelines:  I'm posting this to get it out there. I'd love to see comments that take the ideas forward, but criticism of my argument won't be as useful at this time, in part because I won't do any further work on it. This is a post I drafted in November 2023, then updated for an hour in March 2025. I don’t think I’ll ever finish it so I am just leaving it in this draft form for draft amnesty week (I know I'm late). I don’t think it is particularly well calibrated, but mainly just makes a bunch of points that I haven’t seen assembled elsewhere. Please take it as extremely low-confidence and there being a low-likelihood of this post describing these dynamics perfectly. I’ve worked at both EA charities and non-EA charities, and the EA funding landscape is unlike any other I’ve ever been in. This can be good — funders are often willing to take high-risk, high-reward bets on projects that might otherwise never get funded, and the amount of friction for getting funding is significantly lower. But, there is an orientation toward funders (and in particular staff at some major funders), that seems extremely unusual for charitable communities: a high degree of deference to their opinions. As a reference, most other charitable communities I’ve worked in have viewed funders in a much more mixed light. Engaging with them is necessary, yes, but usually funders (including large, thoughtful foundations like Open Philanthropy) are viewed as… an unaligned third party who is instrumentally useful to your organization, but whose opinions on your work should hold relatively little or no weight, given that they are a non-expert on the direct work, and often have bad ideas about how to do what you are doing. I think there are many good reasons to take funders’ perspectives seriously, and I mostly won’t cover these here. But, to
Dorothy M.
 ·  · 5m read
 · 
If you don’t typically engage with politics/government, this is the time to do so. If you are American and/or based in the U.S., reaching out to lawmakers, supporting organizations that are mobilizing on this issue, and helping amplify the urgency of this crisis can make a difference. Why this matters: 1. Millions of lives are at stake 2. Decades of progress, and prior investment, in global health and wellbeing are at risk 3. Government funding multiplies the impact of philanthropy Where things stand today (February 27, 2025) The Trump Administration’s foreign aid freeze has taken a catastrophic turn: rather than complying with a court order to restart paused funding, they have chosen to terminate more than 90% of all USAID grants and contracts. This stunningly reckless decision comes just 30 days into a supposed 90-day review of foreign aid. This will cause a devastating loss of life. Even beyond the immediate deaths, the long-term consequences are dire. Many of these programs rely on supply chains, health worker training, and community trust that have taken years to build, and which have already been harmed by U.S. actions in recent weeks. Further disruptions will actively unravel decades of health infrastructure development in low-income countries. While some funding may theoretically remain available, the reality is grim: the main USAID payment system remains offline and most staff capable of restarting programs have been laid off. Many people don’t believe these terminations were carried out legally. But NGOs and implementing partners are on the brink of bankruptcy and insolvency because the government has not paid them for work completed months ago and is withholding funding for ongoing work (including not transferring funds and not giving access to drawdowns of lines of credit, as is typical for some awards). We are facing a sweeping and permanent shutdown of many of the most cost-effective global health and development programs in existence that sa
 ·  · 3m read
 · 
Written anonymously because I work in a field where there is a currently low but non-negligible and possibly high future risk of negative consequences for criticizing Trump and Trumpism. This post is an attempt to cobble together some ideas about the current situation in the United States and its impact on EA. I invite discussion on this, not only from Americans, but also those with advocacy experience in countries that are not fully liberal democracies (especially those countries where state capacity is substantial and autocratic repression occurs).  I've deleted a lot of text from this post in various drafts because I find myself getting way too in the weeds discoursing on comparative authoritarian studies, disinformation and misinformation (this is a great intro, though already somewhat outdated), and the dangers of the GOP.[1] I will note that I worry there is still a tendency to view the administration as chaotic and clumsy but retaining some degree of good faith, which strikes me as quite naive.  For the sake of brevity and focus, I will take these two things to be true, and try to hypothesize what they mean for EA. I'm not going to pretend these are ironclad truths, but I'm fairly confident in them.[2]  1. Under Donald Trump, the Republican Party (GOP) is no longer substantially committed to democracy and the rule of law. 1. The GOP will almost certainly continue to engage in measures that test the limits of constitutional rule as long as Trump is alive, and likely after he dies. 2. The Democratic Party will remain constrained by institutional and coalition factors that prevent it from behaving like the GOP. That is, absent overwhelming electoral victories in 2024 and 2026 (and beyond), the Democrats' comparatively greater commitment to rule of law and democracy will prevent systematic purging of the GOP elites responsible for democratic backsliding; while we have not crossed the Rubicon yet, it will get much worse before things get better. 2. T