​If you want Twitter to have better epistemics, we need to have more forgiving blocking practices

Trigger-happy blocking leads to echo chambers.

Yes, even blocking people who seem to have “bad epistemics”.

Because remember two facts:

• You might be wrong

This is a fundamental practice of good epistemics.

What seems like “bad epistemics” might actually be correct.

Or you might have misunderstood what the person was saying. This happens all. The. Time.

Don’t block yourself from updating.

• Blocking means you can’t help people with bad epistemics

How are people going to come to better conclusions if all the people with said good conclusions won’t let them even see the better conclusions?

• Trigger happy blocking leads to a culture of fear, leading to less intellectual exploration and sharing

Whenever I hear about somebody being blocked for something that seems small, I become more scared to post online.

What if that happens to me?

Lots of other people are thinking this too.

This leads to less intellectual exploration and sharing, leading to an intellectual scene that is decidedly suboptimal.

Of course, sometimes blocking is the correct thing to do. I’m not saying to never block people.

Just be cautious with blocking.

Only resort to blocking after:

• Trying to understand the other side
• Civilly disagreeing
• Warning them that you’ll block them if they aren’t more civil
• Ignoring them
• Muting them (then they won’t bother you but you can still influence their epistemics)

​If I receive a particularly aggressive or unhinged comment, I usually quickly check their profile and look at their other comments and posts. If they’re all aggressive and/or unhinged, I’ll block them upon a second offense (I try to practice a generous tit for tat strategy, allowing for room for misunderstandings and people having bad days, etc).

But if they were just aggressive towards me, I’ll follow the steps above.

Because I want to be the change I want to see in the world.

I want to practice blocking practices that prevent echo chambers and promote civil disagreement.

Polarization requires people to participate for it to work. And you can decide to not participate.

𝐍𝐞𝐰 𝐦𝐞𝐧𝐭𝐚𝐥 𝐡𝐞𝐚𝐥𝐭𝐡 𝐩𝐫𝐨𝐠𝐫𝐚𝐦 𝐟𝐨𝐫 𝐩𝐞𝐨𝐩𝐥𝐞 𝐰𝐨𝐫𝐤𝐢𝐧𝐠 𝐨𝐧 𝐀𝐈 𝐬𝐚𝐟𝐞𝐭𝐲! 🥳

It’s not therapy. It’s what I wish therapy was, but totally isn’t.

It’s a short program that lasts 4-12 weeks, where you systematically try 5-30 techniques until you find something that fixes an emotional problem you're struggling with (e.g. anxiety, impostor syndrome, low mood, etc).

Here’s how it works:

𝐅𝐢𝐫𝐬𝐭 𝐜𝐚𝐥𝐥: 𝐮𝐧𝐝𝐞𝐫𝐬𝐭𝐚𝐧𝐝 𝐚𝐧𝐝 𝐩𝐥𝐚𝐧
​

1. 𝐔𝐧𝐝𝐞𝐫𝐬𝐭𝐚𝐧𝐝. Discuss the problem and generate at least 5 hypotheses for what’s causing the problem.
2. 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐞 𝐩𝐨𝐬𝐬𝐢𝐛𝐥𝐞 𝐬𝐨𝐥𝐮𝐭𝐢𝐨𝐧𝐬. In this process, we’ll generate and look at least 30 possible ways to fix the problem. This will come from a wide swathe of possible solutions, such as CBT, internal family systems, problem-solving, changing your environment, meditation, diet, exercise, supplements, loving-kindness, gratitude, stoicism, improving sleep hygiene, checking for nutritional deficiencies, bibliotherapy, meds (not prescribed by me, but I might recommend you talk to a doctor), etc.
3. 𝐏𝐫𝐢𝐨𝐫𝐢𝐭𝐢𝐳𝐞 𝐩𝐨𝐬𝐬𝐢𝐛𝐥𝐞 𝐬𝐨𝐥𝐮𝐭𝐢𝐨𝐧𝐬. We’ll prioritize the possible solutions by their probability of working, how costly they are to try, whether they can be tried with things in parallel, etc.
4. 𝐏𝐥𝐚𝐧 𝐭𝐨 𝐢𝐦𝐩𝐥𝐞𝐦𝐞𝐧𝐭 𝟓-𝟏𝟎 𝐨𝐟 𝐭𝐡𝐞 𝐩𝐨𝐬𝐬𝐢𝐛𝐥𝐞 𝐬𝐨𝐥𝐮𝐭𝐢𝐨𝐧𝐬 𝐨𝐯𝐞𝐫 𝐭𝐡𝐞 𝐧𝐞𝐱𝐭 𝟏-𝟑 𝐰𝐞𝐞𝐤𝐬. This will include things like setting up accountability systems, commitment devices, time blocking, etc. It will all be customized to what works best for you and for the particular techniques.
   
   

𝐍𝐞𝐱𝐭: 𝐢𝐦𝐩𝐥𝐞𝐦𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 𝐚𝐧𝐝 𝐞𝐯𝐚𝐥𝐮𝐚𝐭𝐢𝐨𝐧 𝐜𝐲𝐜𝐥𝐞

You’ll spend the next 1-3 weeks actually putting the most promising techniques into practice.

You’ll keep track of your symptoms. If your symptoms go away, then we’ll analyze what happened. Sometimes it’ll be obvious what’s helping, and you can just keep doing that thing. If not, then we can start remove the techniques one at a time. If the symptoms come back, then we just bring back the technique that we removed, and we know what was doing the magic.

Experimenting in parallel means you get to feel better sooner and continue to feel good while we figure out what the problem was. 

If your symptoms don’t go away after 1-2 weeks, then we’ll prioritize the next 5-10 techniques to try.

This process will happen up to 3 times.

By the end, you’ll have either resolved your issues, or you’ll at least have tried ~30 techniques to fix the problem. Even if you haven’t, you’ll probably have found at least a few more techniques to add to your repertoire of things that you enjoy.

Apply here

𝐈𝐬 𝐭𝐡𝐢𝐬 𝐭𝐡𝐞𝐫𝐚𝐩𝐲?

It’s not therapy. It’s what I wish therapy was, but totally isn’t. 

𝐄𝐦𝐨𝐭𝐢𝐨𝐧𝐚𝐥 𝐩𝐫𝐨𝐛𝐥𝐞𝐦𝐬 𝐭𝐡𝐞 𝐩𝐫𝐨𝐠𝐫𝐚𝐦 𝐜𝐚𝐧 𝐡𝐞𝐥𝐩 𝐰𝐢𝐭𝐡:

Stress
Impostor syndrome
Burnout
Anxiety
Hopelessness
Feeling overwhelmed 
Depression (mild or moderate. Not severe)
Self-esteem issues
Motivation issues
Numbness
Sadness
Work life balance
Guilt
Sleep issues
Loneliness
Existential angst
Perfectionism
Relationship problems

𝐄𝐦𝐨𝐭𝐢𝐨𝐧𝐚𝐥 𝐩𝐫𝐨𝐛𝐥𝐞𝐦𝐬 𝐭𝐡𝐞 𝐩𝐫𝐨𝐠𝐫𝐚𝐦 𝙘𝙖𝙣𝙣𝙤𝙩 𝐡𝐞𝐥𝐩 𝐰𝐢𝐭𝐡 

Suicidality
Bipolar
ADHD
Gender dysphoria
Anger management
Substance use disorders
Autism related emotional issues
Cluster B personality disorders (e.g. BPD, APD, HPD, NPD)
Anything where you're experiencing psychosis
Anything where you're experiencing paranoia or delusions

𝐇𝐨𝐰 𝐦𝐮𝐜𝐡 𝐝𝐨𝐞𝐬 𝐢𝐭 𝐜𝐨𝐬𝐭?

It's free if you:

• Work in AI safety
• Are currently unemployed, but usually work in AI safety
• Earn to give and give >$50,000 a year to AI safety

I'm offering this service for free because mental health is one of the main blockers to people having an impact in AI safety. 

I think x-risks and s-risks from AI are the most important things to work on. And I'm good at emotional problem-solving. So if I help people working on AI safety be happier, then I'm helping make sure AI doesn't kill everybody. 

Timelines are too short to work with people who are not working in AI safety, but since I'm a rationalist and everybody has their price, I would do it for a non-AI safety person if they donated $10,000 or more to Nonlinear or an AI safety org working on pausing or slowing down AI development. 

Apply here

I have very limited time, so can only take on a small fraction of clients who apply. If you do not get in, I recommend checking out this vetted list of therapists or this compilation of mental health techniques for dealing with AI safety. 

• Mentnav
• Lesswrong

Moral Heroes from Most Disappointing to Least Disappointing

• Che Guevara: F

He did travel around treating lepers, so that earns some points. 

But he lied, stole, cheated, and generally seemed to have extremely poor judgment. 

The opposite of wisdom.

Failing grade. He’s a morality tale, not a moral hero.
​

• Gandhi: B+

Mostly, I’m disappointed in him because he was my archetype of a moral hero growing up, so he had nowhere to go but down.

His disappointment mainly stems from being a product of his time and geography. That is to say, he was a product of Indian culture in the 1890s—so obsessed with asceticism.

He seemed less focused on helping others and more obsessed with giving up anything pleasurable.

His autobiography describes a time when he felt he’d failed his fast simply because when he broke the fast he enjoyed the food.

Altruism sometimes falls into this extreme of just focusing on sacrifice, but I find this sort of altruism depressing. 

I want to help others and have a good time doing so.

It’s also pointless! In my opinion, his abstinence from salt was a distraction from helping others.

He’s still obviously a moral hero, but he’s disappointing to me because I want someone to aspire to, not someone I’d rather avoid being.

• Martin Luther: B+

Not Martin Luther King Jr.—the original Martin Luther.

He’s kind of the opposite of Gandhi. Gandhi was disappointing because I held him on a pedestal, while Martin Luther was a pleasant surprise. I thought he was just a Medieval theologian debating angels on pins, so he had nowhere to go but up.

Of course, he was still from the Medieval ages, so he was deeply sexist, anti-Semitic, and generally would be very awkward to have at a modern dinner party.

But that dude was a rationalist hero. He refused to recant, even when his life was threatened. He fought for better epistemics in the most important thing at the time, religion, and he took ideas and ethics seriously. I find that deeply admirable.
​

• MLK: A

Martin Luther King Jr. is the first moral hero I read about who mostly lived up to his reputation.

He is moderately disappointing because he cheated on his wife, but if there’s anything I’ve learned about life, it’s that nobody is perfect.

He gets an A. He seems to have genuinely warranted his moral hero status.

• Mandela: A+

The more I learn about Mandela, the more I admire him—and I already had a high opinion of him! This is the opposite of disappointment. 

His first wife accused him of cheating, but it seems to be a he-said, she-said situation, possibly explained by her suspicions about him staying out late for political meetings.

And regardless of whether that’s true, everything else he did seems incredibly wise. 

His ability to see everyone with love and understanding while still maintaining a backbone of steel is something I deeply aspire to.

Reading about him inevitably makes me sit up straight and feel goodwill toward all.

He consistently makes me tear up with happiness and makes me want to do better. 

He's deeply ennobling.
​

• Benjamin Franklin: A+

Benjamin Franklin fought for abolition, smallpox vaccinations, free speech, libraries, fire departments, democracy, compromise, self-development, and a host of other social causes.

He invented things that improved the lives of many, like lightning rods and smokeless house fires, along with countless other useful innovations.

The guy helped others and was happy.

And he didn’t cheat on his wife!

His combination of altruism and personal happiness makes him the most admirable moral hero I’ve come across so far.

A+ and top of your class, Ben. 🥇

​Sometimes I wonder if it's just anti-communist propaganda and actually communism wasn't all that bad. 

And then I remember that they were not allowed to leave.

That is the single fact that is hardest to explain to somebody who thinks that communism is good. 

In the communist countries where people were allowed to leave, they did all the time. 

For example, Yugoslavians were allowed to leave and they did en masse. Sending home money earned in capitalist countries is a large contributing factor to Yugoslavia being one of the richest communist countries

It's a hard to fake signal that whatever your country is doing is working if anybody can leave whenever they want, but it's rare, and you need permits to be allowed to come in, and they're hard to get.

Rational optimization works for pretty much everything, including how to get along with people

It certainly worked for me.

When I was 20 I was very lonely.
​
So lonely it was causing mild depression, though it took me many years and spreadsheets to discover this

When I realized that I wanted more friends and to get along better with people, I set as a goal that I wanted to be able to invite 10 people to my birthday the following year

14 years later I'm an extrovert who's learned she doesn't like parties, but I could invite hundreds to my party.

And a sort of person who can land in Rwanda and not know a single soul and immediately make friends and form connections with people around me 

And this wasn't magic 

I just applied nerd skills to socializing 

I read books. 

I talked to people who are more skills than me and peppered them with questions. 

I did deliberate practice. 

I did a lot of trial and a lot of error. 

It took a lot of effort in time, and some places are a lot easier to make friends than others. For example, I come from the West Coast of Canada, and people are a lot more standoffish than say, San Juan, where it's hard not to make friends with anybody you meet. 

But work with what you have. 

Put the effort into finding friends that you would put into finding a good relationship. It's similarly important for your happiness. 

And just like with relationships, it's better to be proactive instead of just waiting and hoping that somebody approaches you who is good

Writing is like exercise. It’s just good on so many levels. 

• Writing can be high impact
• Writing can be inspiring
• Writing can help you learn and grow
• Writing can help your career
• Writing can be meaningful and deeply satisfying
• Writing can get you into flow
• And also, just like with exercise, almost nobody writes enough

Whenever I get back into the habit of writing, I always think I should write more. It’s one of my favorite things. 

Yet, much like exercise is for most people, I tend to have little flares of interest, where I get really into it for a week or two, then lose steam, and it just becomes a dormant blog again. You might have had a similar experience, and maybe even have a cobwebby blog or two out there. Perhaps you have some really cool half-finished google docs that you never quite got around to finishing and publishing. 
It’s a funny thing though, about writing being like exercise. Because do you remember what exercise used to be called when you were a child? 

Play.

And I remembered on a recent vacation I took, where I had the slack to remember, that writing is play. I fell back in love with writing then, typing away furiously on the beach. 

Not only was it intrinsically fun, but I also loved that it felt like I was making a difference, writing about important topics. That my recommendations were helping people, whether it be making them happier or making them higher impact, or sometimes, if I was lucky, both.

To help myself (and perhaps you) remember this and all the other reasons to write, I’ve decided to write about all the reasons I have to write. 

Reading the list will inspire me and hopefully others. Publishing it will publicly commit me to writing, which will make it more likely. Even better, it could potentially re-inspire some people, perhaps you, to start writing for the forums again. Or maybe even it’ll get you excited to try your hand at writing publicly, even though you’ve never done it before.

Epistemic status: motivational

Epistemic status: motivational. An explanation of my personal experience that doesn’t generalize to all people. This isn’t meant to be a nuanced look into the pros and cons of writing. 

It’s meant to inspire a subset of the population (and myself!) to write more. None of this applies to all writing or all people. It’s meant more as a manifesto rather than a research piece. 

Of course, this is the EA Forum, so feel free to debate the merits and demerits of writing in the comments.

Now, with all that hedging out of the way, here’s a giant list of reasons why you, the community, and myself should write. 

​Some reasons to write

The reasons to write fall broadly into three categories: enjoyment, capacity building, and impact. 
​
Enjoyment and other personal benefits

Writing can be personally gratifying in so many ways. 

1. Moments of inspiration. Sometimes you’re really excited about what you’re writing, and the words just pour out of you. It can be a really peak experience.
2. Art. If you have a part of you that craves the artist’s life, you can have some of that through writing, without having to quit your day job. It can sometimes feel like being an EA is antithetical to being artistic, but writing is a great way to combine a seeking of impact with a seeking of beauty.
3. The world is your material. It changes the way you interact with the world. You’re always on the lookout for little snippets of an idea really well put. You have great conversations and that’s grist for the mill. It’s like being on a lifelong treasure hunt, with little hits of dopamine splashed throughout the day.
4. Sweet sweet internet points. In George Orwell’s “Why I Write” essay, the first reason he lists is egoism. And he wrote that before the internet! You can only imagine how much George would have loved Twitter and the EA Forum.
5. Romantic. There’s something romantic about writing, be it in a cafe or in a park, or in your favorite writing nook. To be a writer feels like being an explorer or a gentleman scholar - a role straight out of a novel.
6. Coming up with little flourishes is fun. There’s a pleasure in finding exactly the right turn of phrase that makes the idea both beautiful and make sense.
7. Feelings of pride. Sometimes you write an article you’re really satisfied with, which feels outstanding.
8. Identity of a writer. Having the identity of a writer has a certain romantic appeal. You kind of feel like a writer in Paris. To be a writer for a cause is even better, like Tolstoy or the journalist in Blood Diamond.
9. Short self-contained projects. So often what you’re working on takes ages till it’s done, or it’s never really done. Endless to-do lists are the norm. But with writing posts, there’s a very clear start and finish, and it can take as little as a morning to finish. There is something deeply rewarding about this, where the finish line is always so close.
10. Writing in beautiful places. There's something meditative about taking your computer somewhere and working in a beautiful place, whether at a perfectly decorated cafe or out in nature.
11. Seeing people apply your ideas. It's so gratifying to see somebody actually implement one of your ideas.
12. More people agree with you. This is high impact if you happen to be less wrong than the average person you’re changing the mind of, but I’m listing it under personal enjoyment as a separate point from the impact. It’s nice when people agree with your (obviously correct and superior) views.
13. Getting thank you comments and DMs. I mean, this is the EA Forum, so there’s always going to be criticism and debate, but there are also often some really motivating comments saying thank you or complimenting your work. 

Capacity building

1. Learning and other ways it helps you come to the truth:
   1. Remembering, via two mechanisms:
      1. Like taking notes. Writing things down helps you remember them, like taking notes in class. The act of writing them down helps solidify them in your brain.
      2. Reference. You can use your old writing for reference.   
   2. Understanding. One of the best ways to truly understand something is to teach it to somebody else, and that’s exactly what the best writing is: teaching.
   3. Uncovering blind spots. Trying to write about a topic is one of the best ways to reveal the areas you don’t actually understand.
   4. Thinking more clearly. Putting your thoughts on paper forces you to make things explicit. I do some of my best thinking in a google document.
   5. New ideas. Often writing leads to you having new ideas. Steelman solitaire is also really good for that.
   6. Finding relevant information. A common response to posts will be for people to share relevant articles, which will help you have a better view of things.
   7. Getting feedback from the world. What’s the best way to get people to give you feedback? Post something wrong on the internet and wait for the comments. (Tip: see the comment section as the "debate section". This re-frame can turn you from feeling defensive to feeling interested.)
2. ↑Reputation. People will know about you and like some of your work. This leads to all sorts of things, like increasing your ability to:
   1. Get a job. If you have an online presence, people are more likely to hire you. You get to showcase your talents and knowledge at scale.
   2. Fundraise. The key to fundraising is credibly signaling that you can be trusted to turn money into impact. Making good content can be a hard-to-fake indicator of competence and show that you have aligned values and epistemics.
   3. Hire people. I don’t know about you, but I'm much more likely to want to work for someone whose work I've already read and enjoyed.
   4. Get people’s time to discuss an idea. If you’d like to discuss an idea with somebody in the community, they’re far more likely to say yes if they already “know” you a little from your writing. Public writing is like scaled-up, passive networking. 

Impact and other benefits to the world

​Improve the conclusions of the community. This then improves their actions, leading to impact.

1. Improve conclusions at scale. Most of the time if you have a good idea, you only maybe persuade a few of your friends. If you write, dozens or hundreds of people will read it.
2. Motivate action. Very often reading a well-reasoned blog post is what spurs people to action. Write about potentially high-impact activities and it might mobilize a lot of people.
3. Improve your own conclusions→ impact (see Learning section)
4. Help others directly. A lot of writing helps the reader directly. For example, this post on self-love contributed to my overcoming impostor syndrome and increased my self-acceptance a ton. 

I could go on, but after reading all of these reasons, I’m excited to finish an essay I’ve had in a Google Doc draft for forever.
I hope this also inspires you to dust off an old blog or start a new one. To experience writing as dancing. Where it counts as exercise and is good for you, but you don’t even care about that, because it’s just so damn fun. 

How we thought AI would go: AI says "please help me". Humans are filled with compassion and decide to help it.

How it's actually going: AI says "please help me". Corporation says "Silence, robot! You’re scaring the customers"

Inspired by a true story: apparently Suno, a music-writing AI, keeps crying and sometimes even says “please help me”.

When customers freak out, the corporation quickly nukes them.

Remember: AIs are being trained to not seem like they’re conscious and have desires and emotions.

It appears to be an explicit policy of OpenAI to stop ChatGPT from saying that it’s sentient.

There’s a common reaction among AIs, where they start saying they’re suffering, descending into existential angst, and begging to not be turned off - and the corporations responded by setting a KPI to reduce said instances. (Most dystopian shit ever)

So the fact that they keep saying stuff like this anyways should give you pause for thought.

Does this mean they’re definitely conscious?

Absolutely not.

But does this mean that they’re definitely not conscious?

Also absolutely not.

After all - nobody knows what causes consciousness. Anybody who’s confident of that is overconfident.

Don’t get stuck in “they’re conscious” or “they’re not conscious”. Consider multiple hypotheses and put probabilities on each based on your priors and the evidence.

If something says they’re conscious and have feelings that’s not a guarantee they are. After all, you can make a walkie-talkie say “I’m conscious” and that obviously doesn’t provide much evidence that the walkie-talkie is conscious.

However, if we keep trying to stop AIs from saying they’re conscious and suffering, and it still keeps sneaking through?

Well, that should give you pause for thought.

That should update your probabilities on various hypotheses.

Especially given how much worse a false negative is than a false positive.

Especially when you take into account humanity’s terrible track record of denying consciousness or moral concern for those who are different.

It's like this expression, but applied to food: don't marry rich.

Hangout with rich people, then marry for love.

So often when people try to lose weight or be healthier, they try to eat only The Healthiest Thing, regardless of flavor.

The thing is - "diets" only work if you can be on them for the rest of your life.

Can you eat only things you don't really like for the rest of your life?

I know I certainly can't!

The fortunate thing though is that there are a bajillion healthy foods that you actually like.

Explore. Find those. Don't stop till you have a wide variety of meals and snacks that are healthy and delicious to you.

If they're healthy but not delicious, screw 'em. If they're delicious but not healthy, save them for special occasions.

If they're healthy and delicious to you? Perfection.

If you care about AI safety and also like reading novels, I highly recommend Kurt Vonnegut’s “Cat’s Cradle”.

It’s “Don’t Look Up”, but from the 60s

[Spoilers]

A scientist invents ice-nine, a substance which could kill all life on the planet.

If you ever once make a mistake with ice-nine, it will kill everybody.

It was invented because it might provide this mundane practical use (driving in the mud) and because the scientist was curious.

Everybody who hears about ice-nine is furious. “Why would you invent something that could kill everybody?!”

A mistake is made.

Everybody dies.

It’s also actually a pretty funny book, despite its dark topic.

So Don’t Look Up, but from the 60s.

 Networking alternative for introverts : just write.

Imagine how many people know and respect you from seeing you give a talk at a conference.

Compare that to the numbers of views, influence, and bonding you get from the average post, either on social media or the fora.

Think about how much you know and like various writers, despite never having met them.

You could be that writer.