Jasper Blank

• Jasper Blank 13 Sep 2026 6:45 UTC

  8 points

  3

  on: What pac­ing the fron­tier means for China

  Are there any Chinese speakers here that can tell what the actual vibes in the Chinese government are about this? I suspect lesswrong would benefit a lot from an introduction to Chinese culture on AI in late 2026

• Jasper Blank 7 Sep 2026 6:34 UTC

  3 points

  0

  on: What Is The Align­ment Prob­lem?

  How do we carve out “the system” from “the environment”, i.e. how do we draw a Cartesian boundary, in order to roughly match human instincts like “looks like it’s robustly optimizing for X”? That’s an open question, and probably a special case of the more general question of how humans abstract out subsystems from their environment. (This was actually relevant in the previous section too, but it’s more apparent once agency is introduced.)

  On this problem I think Fernando Rosas made promising progress with The separation principle: where do beliefs and desires come from?. I recommend checking if this makes true progress

• Jasper Blank 31 Aug 2026 13:22 UTC

  2 points

  0

  on: The sep­a­ra­tion prin­ci­ple: where do be­liefs and de­sires come from?

  I really like this direction of thinking. And I would love to see more of it. I have gone I to depth on control theory myself too and I would love to see something like this in current Models trained for Agency

• Jasper Blank 25 Jun 2026 21:35 UTC

  1 point

  0

  on: Feel­ings as post-it notes

  When I was younger I learned through meditation to get into a habit of not sticking with that kind of anguish. And I also tend to forget things I have to do really often to the point that I make sure to write some version of them down in second because otherwise I will forget, maybe because I don’t keep the anguish around.

  I do want to flag that this feels like a really suspicious supporting of feeling bad idea. I believe all of the positive effects should still be possible without a strong negative emotions.

Claims all the way down

• Jasper Blank 13 Jun 2026 16:02 UTC

  2 points

  0

  on: AML for AI as a ver­ifi­ca­tion mechanism

  I am currently working on the future of Life Foundation competition. I hope that out of this challenge we could get a general system that will help in this case too. I will release my initial thoughts on this subject soon

• Jasper Blank 8 Jun 2026 15:07 UTC

  3 points

  −3

  on: Ne­glected Ba­sics of AI Alignment

  What an amazing read. I only discovered HPMOR relatively recently and this reads exactly like Quirrell would discuss this topic. Utterly evil but hard to find the exact hole in the argument.

• Jasper Blank 4 Jun 2026 17:51 UTC

  1 point

  0

  on: Lab Leaks, Black Holes, and Eggs: Epistemic Case Study Competition

  I really like this idea and I would love to participate. I am personally also interesting in finding other people who want to participate and chatting with them, maybe teaming up if there is a good fit. Do you have any plans for support of this kind of cooperation?

• Jasper Blank 3 Jun 2026 15:10 UTC

  5 points

  0

  on: So­ciety Ex­plained: a tool for effi­ciently ex­plor­ing >100 the­o­ries of society

  I really like this idea and it seems very much like the style of this website to try to create an overview of all human thought so far.
  One thing I would love to see is what empirical claims are made by each of these thinkers and how well those hold up in history.

• Jasper Blank 29 Apr 2026 11:43 UTC

  1 point

  0

  on: Thoughts on AI Safety Me­gagame Design

  I really like this direction to go in. I personally have some experience with game design too, and a hell of a lot of experience with role playing games, i would love to get involved in something like this.

• Jasper Blank 29 Apr 2026 11:27 UTC

  3 points

  2

  in reply to: ArisC’s comment on: ArisC’s Shortform

  I haven’t used Talkie myself. I expect it to claim it is conscious, same as first gen models. The great difficulty is still that we don’t know how much it is parroting and how much it can truly introspect.

• Jasper Blank 29 Apr 2026 11:19 UTC

  7 points

  2

  on: Causal in­fer­ence di­ary: skiing causes snow

  Non sequitur but, Skiing does cause snow. Because old ski resorts want to keep running, so they put up snow machines.

• Jasper Blank 24 Apr 2026 11:37 UTC

  5 points

  3

  on: When the World Ends you Will Re­gret Not filling out that Con­tact Us Form

  “We don’t want to be to AI what dogs are to humans” My congress woman at the end of the meeting.

  Ironically humans basically becoming pets is one of the most positive outcomes in the general discourse. That only shows more that we need a better view of what we want, and what normal people would want with these changes.
  
  I personally live in the Netherlands, and i am not really sure what good policy for the Netherlands and the EU would be. From the view of agency I will try to find people to talk with about this

• Jasper Blank 24 Apr 2026 7:58 UTC

  1 point

  0

  on: How To Figure Out Life By Ben Franklin

  Spend all your money on books.

  I can only imagine the insane amount of books you’d get if you spend thousands montly on books. I am still a student so i sometimes use the fact that almost every book is now available as a PDF. And overall i think it is still just as important to read, but money doesn’t seem to be the limit anymore.

• Jasper Blank 22 Apr 2026 13:44 UTC

  2 points

  1

  on: Will Robots Ever Play in the NBA?

  These narratives can still come with Machines. In F1 racing a big part of the story is how each engineering team was able to make their car better for specific parts of the sport. So maybe future robot sports will pull from car racing in that way.

Jasper Blank’s Shortform

• Jasper Blank 21 Apr 2026 11:43 UTC

  1 point

  0

  on: Jasper Blank’s Shortform

  Is there a place to find good text on the internet?
  I am reading “The Future of Everything is Lies, I Guess” and i found this on Hackernews, which along with Lesswrong is currently basically my only source of detailed information on the world. I was wondering, does anybody have better ways of dealing with the sheer size of the internet and how to find good stuff in it?

• Jasper Blank 10 Mar 2026 6:48 UTC

  0 points

  −1

  in reply to: joseph_c’s comment on: Prologue to Ter­rified Com­ments on Claude’s Constitution

  For the person who asked why. I think this is to prevent the model from steering the conversation to predictable places.

• Jasper Blank 6 Mar 2026 10:48 UTC

  3 points

  0

  in reply to: Taylor G. Lunt’s comment on: An­drew_Critch’s Shortform

  To me the next question would be is, does there exist True information that would do the same

• Jasper Blank 15 Feb 2026 18:58 UTC

  7 points

  3

  on: Should any­one’s “anal­y­sis” of ex­tremely com­plex sys­tems, such as geopoli­tics, be taken se­ri­ously? or, Does any­one take a 5 year old’s “anal­y­sis” of de­cently com­plex sys­tems, like big city poli­tics, se­ri­ously?

  I would say that the possibility of analysis is not about the complexity of the total system, but about local wells of stability. So i would say that the fact that Country’s tend to have coherent policies means that their actions can be analyzed without know everything that happens in every country