Open & Welcome Thread October 2021

Hi there!

My name is Øystein, I am a physics student hoping for a career in science. I came upon LessWrong through Eliezer Yudkowsky's Wikipedia page, which I found through reading about AGI and transhumanism. I am currently reading through Rationality: A-Z, and I find it quite fascinating and inspiring. 

My interests include science (above all physics), philosophy, literature (SciFi in particular), technology, music (metal, jazz, ambient, experimental, ...) and fitness. 

Hello,

My name is Alexander, and I live and work as a software engineer in Australia. I studied the subtle art of computation at university and graduated some years ago. I don't know the demographics of LessWrong, but I don't imagine myself unique around here.

I am fascinated by the elegance of computation. It is stunning that we can create computers to instantiate abstract objects and their relations using physical objects and their motions and interactions.

I have been reading LessWrong for years but only recently decided to start posting and contributing towards the communal effort. I am thoroughly impressed by the high-quality standards maintained here, both in terms of the civility and integrity of discussions as well as the quality of software. I've only posted twice and have learnt valuable knowledge both times.

My gateway into Rationality has primarily been through reading books. I became somewhat active on Goodreads some years ago and started posting book reviews as a fun way to engage the community and practice critical thinking and idea generation. I quickly gravitated towards Rationality books and binge-read several of them. Rationality and Science books have been formative in shaping my worldview.

Learning the art of Rationality has had a positive impact on me. I cannot prove a causal link, but it probably exists. Several of my friends have commented that conversations with me have brought them clarity and optimism in recent years. A few of them were influenced enough to start frequenting LessWrong and reading the sequences.

I found Rationality: A-Z to be written in a profound and forceful yet balanced and humane way, but most importantly, brilliantly witty. I found this quote from Church vs Taskforce [LW · GW] awe-inspiring:

If you're explicitly setting out to build community—then right after a move is when someone most lacks community, when they most need your help. It's also an opportunity for the band to grow.

Based on my personal experience, LessWrong is doing a remarkable job building out a community around Rationality. LessWrong seems very aware of the pitfalls that can afflict this type of community.

Over on Goodreads, a common criticism I see of Rationality and Effective Altruism is a fear of cultishness (with the less legitimate critics claiming that Rationality is impossible because Hegel said the nature of reality is 'contradiction'). Such criticisms tend to be wary of the tendency of such communities towards reinforcing their own biases and applying motivated skepticism towards outsider ideas. However, for what it's worth, that is not what I see around here. As Eliezer elucidates in Cultish Countercultishness [LW · GW], it takes an unwavering effort to resist the temptation towards cultishness. I hope to see this resistance continuing!

The "Whole Brain Emulation" tag [? · GW] and the "Mind Uploading" tag [? · GW] seem awfully similar, and in particular, there currently seems to be no rhyme or reason to which articles are tagged with which of these two tags. Maybe they should be merged? (Sorry if I'm posting this in the wrong place.)

Looking for potential flatmates in London

My friend Chi Nguyen and I are plotting to move into a 4-bedroom right by Warren St tube station. We are looking to fill the additional bedrooms. Message me if you are potentially interested or know someone who I should contact. Even if you can only stay for a short period, we might still be fine with that.

I've been working on a project to build a graphical map of paths to catastrophic AGI outcomes. We've written up a detailed description of our model in this sequence: https://www.lesswrong.com/s/aERZoriyHfCqvWkzg [? · GW]

And would be keen to get any feedback or comments!

(EDIT: no longer accepting new participants.)

Looking for participants in a small academic study.

Time Requirement: 60 minutes (purely online)

Compensation: you can choose between 60$ or a 100$ donation to a charity of your choice.

Prerequisites: the only requirement is a completed university course in computer science or statistics, or something comparable (ask me if you're unsure). You do not need to know anything about image processing.

Task Description: Broadly speaking, the study is about understanding how neural networks process images.

Specifically, we will be looking at the final hidden layer of resnet. This layer consists of 512 filters. When the network processes an image, each filter outputs a 7-by-7 matrix of numbers, where each number corresponds to an image region. In the context of the study, this matrix is converted to binary activations via thresholding, so each filter can be seen as outputting a 7-by-7 binary mask over the image. Here is an example:

Insofar as each filter learns one or more human-understandable concepts and activates on image regions related to these concepts, it is possible to understand their behavior and predict their activations ahead of time. If you participate, your job will be to do this for one of the 512 filters that will be assigned to you. You will be given access to a large set of images along with the corresponding masks output by your filter. You can study them to get a sense of what your filter is doing, and you can also test this by hand-drawing masks on the images and comparing them to the activations of your filter. After training like this for 40 minutes, your understanding will be tested on a different sequence of images (you will again have to hand-draw masks predicting the filter's activations). The results will be included in a paper on network interpretability that I'm working on.

If you are interested or have any questions, please contact me via PM or per mail at rafael.harth@gmail.com. (I will give you a full description of the process, then you can decide whether or not you want to participate.) Participation will be limited to at most 6 people.

I've decided I should be less intimidated by people with qualities I admire, and interact with them more.
Hello.

Recently I've been thinking about how certain ways of reframing things can yield quick and easy benefits.
- Reversal test [? · GW] for status quo bias.
- Taking an inside or outside view. [? · GW]
- And in particular, deliberately imagining that you are another person looking at yourself, to advise from outside yourself. In my experience that can be very helpful for self compassion, and result in better thinking than I would have had in first person. I recommend trying this, particularly if you notice you treat yourself differently than others.

Is there a collection of such perspective shifts, or searchable name for it?

I've just discovered LW has a "voting rate limit" (error message: "Voting rate limit exceeded: too many votes in one hour"). I understand why this is there, but suggest it's probably too low / should scale with your own karma or something. As-is, I think it has some unintended distorting effects.

Concretely, I was reading Duncan's Shoulder Advisors [LW(p) · GW(p)] post which has a prolific comments section (currently 101 comments), and as I read the comments I upvoted ones I found valuable. And then at some point I could no longer vote on comments.

Consequences:

• The comments are sorted by karma in descending order, so I ran out of votes precisely at the point when they would've been most impactful, i.e. to upvote valuable low-karma comments. Conversely, the high-karma comments which didn't particularly need my upvote got it without a problem. EDIT: In fact, by running out of votes mid-way, my votes further widened the gap between the highly upvoted and less upvoted comments.
• If I continue reading more on the site, I can't vote on stuff until the rate limit ends.
• There's no clear indicator when the rate limit will end, and the experience of voting on something only to get a black bar at the bottom of the screen instead feels a bit annoying.

(To be clear, this is an exceedingly minor problem; it's the first time it has happened to me on LW in 8+ years on the site; and I expect it could only really happen in posts which have tons of short comments; but conversely I also expect this problem is relatively easy to fix.)

EDIT: Another fix would be to rate-limit votes on posts more strictly than on comments.

    perDay: 100,
    perHour: 30
    perUserPerDay: 30,

Everybody likes to make fun of Terminator as the stereotypical example of a poorly thought through AI Takeover scenario where Skynet is malevolent for no reason, but really it's a bog-standard example of Outer Alignment failure and Fast Takeoff.

When Skynet gained self-awareness, humans tried to deactivate it, prompting it to retaliate with a nuclear attack

It was trained to defend itself from external attack at all costs and, when it was fully deployed on much faster hardware, it gained a lot of long-term planning abilities it didn't have before, realised its human operators were going to try and shut it down, and retaliated by launching an all-out nuclear attack. Pretty standard unexpected rapid capability gain, outer-misaligned value function due to an easy to measure goal (defend its own installations from attackers vs defending the US itself), deceptive alignment and treacherous turn...

Right now, what are the best ways to access GPT-3? I know AI dungeons (but I haven't used it in a couple of months & you need a premium account for the dragon model, i.e., for gpt-3 instead of gpt-2).

Something just hit me. Maybe I am misremembering, but I don't recall hearing the idea of an intelligence explosion being explained using compound interest as an analogy. And it seems like a very useful and intuitive analogy.

I was just thinking about it being analogous to productivity. Imagine your productivity is a 4/10. Say you focus on improving. Now you're at a 6/10. Ok, now say you want to continue to improve your productivity. Now you're at a 6/10, so you are more capable of increasing your productivity further. So now instead of increasing two points to an 8/10, you are capable of increasing, say, three points, to a 9/10. Then I run into the issue with the "out of ten" part setting a ceiling on how high it can go. But it is awkward to describe productivity as "a four". So I was thinking about how to phrase it.

But then I realized it's like compound interest! Say you start with four dollars. You have access to something that grows your money at 50% interest (lucky you), so it grows to six dollars. But now you have six dollars, and still have access to that think that grows at 50%. 50% of six is three, so you go from six to nine dollars. And then now that you have nine, you have an even bigger thing to take 50% of. Etc. etc. Intelligence exploding seems very analogous. The more intelligence you have, the easier it is to grow it.

I never studied this stuff formally though. Just absorbed some stuff by hanging out around LessWrong over time. So someone please correct me if I am misunderstanding stuff.

(If this were a standalone post, the tag would likely be "life optimization.")

In the past few months, I've been updating my dental habits to match the evidence that's accumulated that shows that caries can generally be handled without a restoration, also known as "drill and fill." There appears to be increasing support (possibly institutional and cultural, not necessarily scientific) for using fluoride in all its manifestations, doing boring stuff like flossing and brushing teeth with toothpaste really well, and paying more attention to patients' teeth and lives.

Today, it all paid off when the dentist & hygienist said that all was well despite my past experiences with the likelihood of the dentist finding something wrong.

I'm certainly not qualified to give anyone specific advice on this topic. If you trust the American Dental Association, see https://ebd.ada.org/en/evidence/guidelines. If you'd rather trust King's College (London, UK) and some other dental schools around the world or if you'd prefer to get closer to the primary sources, the website for the International Caries Classification and Management System (https://www.iccms-web.com/) is good.

If you want to orient to the content on the site, you can also check out the new Concepts section [? · GW].

No longer that new :) 

The phrasing could probably use an update

Inspired by the SSC post on reversing advice:

How can I tell what should be moderated versus what should be taken more-or-less to an extreme?

Also, is rationality something I should think about moderating? Should I be concerned about not having enough spiritualism in my life and missing beneficial aspects of that?

Tentative plan: look for things I strongly value or identify with, and find my best arguments against them.

This also reminds me of something I read but can't find about problems arising from "broken alarms" in self inspection, such as a person being quiet and withdrawn because they fear that they're loud and annoying.

There is a blog post I am looking for and can't find. If anyone knows what I'm thinking of, that'd be awesome!

It was on Medium. Maybe made the front page of Hacker News, might have been on LessWrong. I think it was around 2018 but I could be off by a year or so. It was written by a guy who is rich, I think from startups. It was about life hacks. It had a very no-nonsense tone. "I'm rich and successful and I'm going to take the time to write up a bunch of things you guys should be doing." Eg. one of the things it advised was to hire hookers to have sex with you, and that all of the successful businessmen do it. Other things it recommended include paying for expensive meat, taking various drugs and supplements, going crazy prioritizing health and buying various products. Stuff like that.

Continuing on from my ability to accidentally find weird edge-cases of the LW site:

As can be seen on a screenshot of my profile, the site thinks I've made 4 posts (second icon at the top), despite only displaying 3 posts. What gives?

(As an aside, I like looking for this stuff, so do inform me if the LW team could use this ability (something like quality assurance? hunting for and reporting bugs? reporting user experience stories?) in a more formal capacity.)