Jeroen Willems🔸

• Jeroen Willems🔸Jul 9, 2023, 9:04 AM

  24 points

  9 ∶ 0

  on: OpenAI is start­ing a new “Su­per­in­tel­li­gence al­ign­ment” team and they’re hiring

  We are dedicating 20% of the compute we’ve secured to date over the next four years to solving the problem of superintelligence alignment.

  This may sound like a lot, but I think it’s likely that 4 years from now 20% of currently secured compute will just be a tiny fraction of what they’ll have secured by then.

• Jeroen Willems🔸Jul 9, 2023, 8:53 AM

  2 points

  0 ∶ 0

  on: An­nounc­ing the EA Archive

  What’s the likelihood that even in ‘incredible’ places there would be electricity? For some reason I always assumed there would basically be no electricity during a major global catastrophe, which is possibly incorrect. But does it make sense to have paper copies too? What’s the trade-off here?

• Jeroen Willems🔸Jun 20, 2023, 9:38 AM

  2 points

  0 ∶ 0

  in reply to: Jeroen Willems🔸’s comment on: Jeroen_W’s Shortform

  Reason why I call it a “stream of consciousness”: Streams change over time. Conscious beings do too. They can also split, multiply or grow bigger.

  One thing I worry about though: Does your consciousness end when sleeping? Does it end when under anesthesia? These thoughts frighten me.

• Jeroen Willems🔸Jun 19, 2023, 8:06 PM

  4 points

  0 ∶ 1

  on: Jeroen_W’s Shortform

  An unpolished attempt at moral philosophy

  Summary: I propose a view combining classic utilitarianism with a rule that says not to end streams of consciousness.

  Under classic utilitarianism, the only thing that matters is hedonic experiences.
  People with a person affecting view object to this, but that view comes with issues of its own.
  
  To solve the tension between these two philosophies, I propose a view that adds a rule to classical utilitarianism disallowing directly ending streams of consciousness (SOC)
  
  This is a way to bridge the gap between the person-affecting view and ‘personal identity doesn’t exist’ view and tries to solve some population ethics issues.
  
  I like the simplicity of classic utilitarianism. But I have a strong intuition that a stream of consciousness is valuable intrinsically, meaning that it shouldn’t be stopped/​destroyed. Creating a new stream of consciousness isn’t intrinsically valuable (except for the utility it creates).
  
  A SOC isn’t infinitely valuable. Here are some exceptions:
  1. When not ending a SOC would result in more SOCs ending (see trolley problem): basically you want to break the rule as little as possible
  2. The SOC experiences negative utility and there are no signs it will become positive utility (see euthanasia)
  3. Ending the SOC will create at least 10x its utility (or a different critical level)
  
  I believe this is compatible with the non-identity problem (it’s still unclear who’s you if you’re duplicated or if you’re 20 years older).
  But I’ve never felt comfortable with the teleportation argument, and this intuition explains why (as a SOC is being ended).
  
  So generally this means: Making current population happier (or making sure few people die) > increasing amount of people
  
  Future people don’t have SOCs as they don’t exist yet, but it’s still important to make their lives go well.
  
  Say we live in a simulation. If our simulation gets turned off and gets replaced by a different one of equal value (pain/​pleasure wise), there still seems to be something of incredible value lost.
  
  Still, if the simulation gets replaced by a sufficiently more valuable one it could still be good, hence exception number 3. The exception also makes sure you can kill someone to prevent future people never coming into existence (for example: someone is about to spread a virus that makes everyone incapable of reproducing).
  
  I don’t think adding this rule changes the EV calculations regarding increasing pain/​pleasure of present and future beings when it doesn’t involve ending streams of consciousness (I could be wrong though).
  
  This rule doesn’t solve the repugnant conclusion, but I don’t think it’s repugnant in the first place. I think my bar for a life worth living seems higher than those of other people.
  
  How I came to this: I really liked this forum post arguing “Making current population happier > increasing amount of people”. But if I agree it means there’s something of value besides pure pleasure/​pain. This is my attempt at finding what it is.
  
  One possible major objection: If you’re giving birth you’re essentially causing a new SOC to be ended (as long as aging isn’t solved). Perhaps this is solved by saying you can’t directly end a stream of consciousness, but you can ignore second/​third order effects (though I’m not sure how to make sense of that).

  I’d love to hear your thoughts on these ideas. I don’t think these thoughts are good enough or polished enough to deserve a full forum post. I wouldn’t be surprised if the first comment under this shortform would completely shatter this idea.

• Jeroen Willems🔸Jun 6, 2023, 10:44 PM

  4 points

  0 ∶ 0

  in reply to: Sharang Phadke’s comment on: Feed­back re­quested: EA Fo­rum reactions

  I’d personally much rather have agree/​disagree on posts than these reactions, if we had to pick. I’m not sure if these reactions add any useful information. But I’m happy to see you’re trying to make it simpler than at LessWrong. Curious to hear what the other reasons are for no agree/​disagree on posts. I frequently upvote posts I disagree with and would like to express that disagreement without writing a comment. Maybe agree/​disagrees can be optionally set by the authors of the post?

• Jeroen Willems🔸Jun 6, 2023, 10:38 PM

  2 points

  0 ∶ 0

  in reply to: EdoArad’s comment on: Feed­back re­quested: EA Fo­rum reactions

  Very much agree. I use upvotes/​downvotes to indicate what I would like to see more/​less of on the forum. Making that clearer in the pop-up would be great!

• Jeroen Willems🔸Jun 4, 2023, 8:48 AM

  6 points

  0 ∶ 0

  in reply to: Nathan Young’s comment on: Nathan Young’s Shortform

  This is exactly why I mostly give to animal charities. I do think there’s higher uncertainty of impact with animal charities compared to global health charities so I still give a bit to AMF. So roughly 80% animal charities, 20% global health.

• Jeroen Willems🔸May 30, 2023, 7:59 AM

  4 points

  0 ∶ 0

  on: New Video: What to Eat in a Global Catastrophe

  Great job Christian and Jenna!

• Jeroen Willems🔸May 25, 2023, 8:19 AM

  3 points

  0 ∶ 0

  on: How I solved my prob­lems with low en­ergy (or: burnout)

  Thank you so much for sharing this! I’d personally love to read the appendix. I struggle hard with understanding the feelings and sensations in my body, but I feel quite confident that my main cause of fatigue is stress or anxiety. Mostly because relaxation techniques (breathing exercises, chamomile tea,...) seem to increase my energy levels.

  Also with big tasks breaking them down really helps :)

• Jeroen Willems🔸May 24, 2023, 12:30 PM

  5 points

  1 ∶ 0

  on: Fo­rum up­date: Tri­al­ling recom­men­da­tions & and many other changes (May 2023)

  I would suggest keeping the recommended posts optional. I like them a lot, but I worry they might keep me on the forum too long. They can definitely be on by default.

• Jeroen Willems🔸May 12, 2023, 12:42 PM

  6 points

  2 ∶ 0

  on: How much fung­ing is there with dona­tions to differ­ent EA an­i­mal char­i­ties?

  This isn’t about the main question you raise in this post, but I’m curious why you think biorisk reduction would increase expected future suffering.

• Jeroen Willems🔸May 5, 2023, 3:41 PM

  10 points

  2 ∶ 0

  on: AI X-risk in the News: How Effec­tive are Re­cent Me­dia Items and How is Aware­ness Chang­ing? Our New Sur­vey Re­sults.

  This is really valuable research, thank you so much for sharing it!

• Jeroen Willems🔸May 5, 2023, 3:38 PM

  8 points

  3 ∶ 0

  in reply to: Jeff Kaufman 🔸’s comment on: Get­ting Cats Ve­gan is Pos­si­ble and Imperative

  Yeah I think this is a really important part of the discussion. We won’t get a world filled with vegan cats unless owners don’t have to worry about constantly checking pH levels.

• Jeroen Willems🔸Apr 22, 2023, 4:50 PM

  3 points

  0 ∶ 0

  in reply to: Bary Levy’s comment on: If your AGI x-risk es­ti­mates are low, what sce­nar­ios make up the bulk of your ex­pec­ta­tions for an OK out­come?

  “without regard for other species” is doing a lot of work

• Jeroen Willems🔸Apr 21, 2023, 4:00 PM

  12 points

  3 ∶ 4

  on: If your AGI x-risk es­ti­mates are low, what sce­nar­ios make up the bulk of your ex­pec­ta­tions for an OK out­come?

  My estimates aren’t low, I think there’s very roughly about 40% chance we’ll die because of AI this century. But here are some reasons why it isn’t higher:

  1. Creating a species vastly more intelligent than yourself seems highly unusual, nothing like it has happened before, so there need to be very good arguments for why it’s possible.

  2. Having a species completely kill all other species is also very unusual, so there need to be very good arguments for why that would happen.

  3. Perhaps AGI won’t be utility maximizing, LLMs don’t seem to be very maximizing. If it has a good model of the world maybe it’ll understand what we want and just give us that.

  4. Perhaps we’ll convince the world to slow down AI capabilities research and solve alignment in time.

  There are good counterarguments to these which is why my p(doom) is so high, but they still add to my uncertainty.

• Jeroen Willems🔸Apr 20, 2023, 8:23 PM

  10 points

  4 ∶ 0

  in reply to: MaxRa’s comment on: Sta­tus Reg­u­la­tion in EA

  Same, been active since 2016 and these seem odd to me. I would say anyone who’s really interested in the question of how to help others effectively using reason and evidence is an EA.

• Jeroen Willems🔸Apr 11, 2023, 10:02 AM

  1 point

  0 ∶ 0

  in reply to: D0TheMath’s comment on: Which stocks or ETFs should you in­vest in to take ad­van­tage of a pos­si­ble AGI ex­plo­sion, and why?

  Yeah I’ve asked the same question (why invest in AI companies when we think they’re harmful?) twice before but didn’t get any good answers.

EA Belgium is look­ing for a Com­mu­nity Builder!

Can We Pos­i­tively Im­pact The Fu­ture? (A Hap­pier World video)

• Jeroen Willems🔸Mar 31, 2023, 4:48 PM

  2 points

  0 ∶ 0

  in reply to: Violet Hour’s comment on: See­ing more whole

  Thank you!!