Difference between revisions of "List of AI safety projects I could work on"

From Issawiki
Jump to: navigation, search
(Exposition of technical topics)
 
(10 intermediate revisions by the same user not shown)
Line 1: Line 1:
 
(November 2020)
 
(November 2020)
  
evening tier = I can make useful/meaningful progress within one hour and even when I am somewhat tired from having done other stuff during the day (at the limit, think of things like [[Duolingo]] where each task can be accomplished in a few seconds)
+
evening tier = I can make useful/meaningful progress within one hour and even when I am somewhat tired from having done other stuff during the day (at the limit, think of things like [[Duolingo]] where each task can be accomplished in a few seconds). This doesn't mean I can ''complete'' a task within one hour; completion may require several evenings. But at least a single evening can make progress in a way that doesn't require "re-doing" the same step (because I lost whatever context I had when working on it initially), and a single evening can also make definite progress (rather than feeling lost or demotivated because it requires having good ideas and I can't generate ideas when I'm tired).
  
 
weekend tier = I can make useful progress if I make it my main thing for a single day, e.g. on a weekend day. Alternatively, I can make progress within 1-2 hours as long as I am mentally alert and feeling fine.
 
weekend tier = I can make useful progress if I make it my main thing for a single day, e.g. on a weekend day. Alternatively, I can make progress within 1-2 hours as long as I am mentally alert and feeling fine.
  
 
vacation tier = I need more than a day or two of concentrated "good" time to focus on this, either because the task itself is not clearly defined (so I need to do lots of brainstorming and thinking to figure out next steps), or because it requires keeping lots of things in my head so I cannot be context-switching with other tasks (i.e. if I work on it for a few hours, then I might get distracted by another project and forget what I was doing)
 
vacation tier = I need more than a day or two of concentrated "good" time to focus on this, either because the task itself is not clearly defined (so I need to do lots of brainstorming and thinking to figure out next steps), or because it requires keeping lots of things in my head so I cannot be context-switching with other tasks (i.e. if I work on it for a few hours, then I might get distracted by another project and forget what I was doing)
 +
 +
==Increase activity on LessWrong==
 +
 +
* Ask lots of questions on LW, e.g.:  (duration tier depends on question; I believe I can rush through and ask certain questions within an hour which would be evening tier or weekend tier)
 +
** Applicability of FDT/UDT/TDT to everyday life https://github.com/riceissa/project-ideas/issues/44
  
 
==Writing up my opinions==
 
==Writing up my opinions==
  
* writing some sort of overview of my beliefs regarding AI safety. like, if i was explaining things from scratch to someone, what would that sound like? (big chunk)
+
* writing some sort of overview of my beliefs regarding AI safety. like, if i was explaining things from scratch to someone, what would that sound like? (vacation tier)
* my current take on [[AI timelines]] (big chunk)
+
* my current take on [[AI timelines]] (vacation tier)
* my current take on [[AI takeoff]] (big chunk)
+
* my current take on [[AI takeoff]] (vacation tier)
* my current take on MIRI vs Paul (big chunk)
+
* my current take on MIRI vs Paul (vacation tier)
  
==Research projects==
+
==Personal reflection==
  
* continue working out [[AI takeoff]] disagreements (big chunk)
+
* reflection post about getting involved with AI safety (vacation tier)
* continue working out MIRI vs Paul (big chunk)
 
* HRAD paper with [[David Manheim]] (big chunk)
 
* concrete plausible scenarios for what could happen when AGI comes around (big chunk)
 
* deep dive into human evolution to figure out what the heck it might tell us about AI takeoff/AI timelines (big chunk)
 
* comparison of AI and nukes (big chunk)
 
* think about [[AI polarization]], using examples like COVID and climate change (big chunk)
 
* write up my understanding of people's views on [[whole brain emulation]] (big chunk)
 
  
==Technical AI safety==
+
==Exposition of technical topics==
  
* I still don't feel motivated to do this since I don't feel convinced by any existing worldview/visualization that has been put forth (by e.g. MIRI or Paul) (big chunk)
+
* [[Solomonoff induction]] guide (I think I've already figured out things here that are not explained anywhere, so I think I could write the best guide on it, but it's not clear how important this is for people to understand) (vacation tier)
 +
* [[Judea Pearl|Pearl]] [[belief propagation]] guide (vacation tier)
 +
* reflective oracles might be another good option here
 +
* Summarizing/distilling work that has been done in [[decision theory]] (vacation tier)
 +
* starting something like [[RAISE]]; see [[There is room for something like RAISE]] (vacation tier)
 +
* Doing something more like "tools for thought" or "[[explanation science]]" research, with AI safety as the [[serious context of use]]
  
 
==AI safety wiki==
 
==AI safety wiki==
  
* Writing articles for AI safety wiki (big chunk)
+
* Writing articles for AI safety wiki (some pages are evening tier or weekend tier, but thinking strategically about what to write for the wiki is vacation tier)
  
 
==The Vipul Strategy==
 
==The Vipul Strategy==
  
* Expanding [[AI Watch]] to cover agendas, documents, more people/orgs with more columns filled in, graphs, automated [https://aiwatch.issarice.com/compare.php?by=organization&for=2020 yearly review] of orgs, etc. (chunk size depends on task -- adding data is small chunk but bigger strategic additions are big chunk)
+
* Expanding [[AI Watch]] to cover agendas, documents, more people/orgs with more columns filled in, graphs, automated [https://aiwatch.issarice.com/compare.php?by=organization&for=2020 yearly review] of orgs, etc. (duration tier depends on task -- adding data is evening tier but bigger strategic additions are weekend tier or vacation tier)
* Updates to timeline of AI safety and other relevant timelines (small chunk)
+
* Updates to timeline of AI safety and other relevant timelines (evening tier)
* Timeline of [[Eliezer Yudkowsky]] publications https://github.com/riceissa/project-ideas/issues/16 (small chunk)
+
* Timeline of [[Eliezer Yudkowsky]] publications https://github.com/riceissa/project-ideas/issues/16 (evening tier)
* Wikipedia pages for AGI projects https://github.com/riceissa/project-ideas/issues/22 (big chunk)
+
* Wikipedia pages for AGI projects https://github.com/riceissa/project-ideas/issues/22 (vacation tier to figure this out; writing an individual page is likely weekend tier)
  
==Increase activity on LessWrong==
+
==Research projects==
  
* Ask lots of questions on LW, e.g.(chunk size depends on question; I believe I can rush through and ask certain questions within an hour)
+
* continue working out [[AI takeoff]] disagreements (vacation tier)
** Applicability of FDT/UDT/TDT to everyday life https://github.com/riceissa/project-ideas/issues/44
+
* continue working out MIRI vs Paul (vacation tier); e.g. read through the late 2021 MIRI conversations now that that's out
 +
* concrete plausible scenarios for what could happen when AGI comes around (vacation tier)
 +
* deep dive into human evolution to figure out what the heck it might tell us about AI takeoff/AI timelines (vacation tier)
 +
* comparison of AI and nukes (vacation tier)
 +
* think about [[AI polarization]], using examples like COVID and climate change (vacation tier)
 +
* write up my understanding of people's views on [[whole brain emulation]] (vacation tier)
 +
* clarify my thoughts on probability of saving the world via x-risk reduction (vacation tier)
 +
* Philosophy
 +
** human values/[[deliberation]] (vacation tier)
  
==Exposition of technical topics==
+
==Learn stuff==
  
* [[Solomonoff induction]] guide (I think I've already figured out things here that are not explained anywhere, so I think I could write the best guide on it, but it's not clear how important this is for people to understand) (big chunk)
+
* learn more machine learning so I can better follow some discussions (weekend tier as long as I am diligent to use [[Anki]] to review partial progress)
* [[Judea Pearl|Pearl]] [[belief propagation]] guide (big chunk)
+
* learn more economics. I somewhat often feel confused about how to think about various AI strategy questions (e.g. history of growth, how AI systems might cooperate and increase economies of scale, what percentage of GDP might be used for computing costs) and I suspect part of the reason is that I don't know enough economics. (weekend tier as long as I am diligent to use [[Anki]] to review partial progress)
* Summarizing/distilling work that has been done in [[decision theory]] (big chunk)
+
* understand the [[neuromorphic AI]] pathways that people like [[Steve Byrnes]] and [[gwern]] have been talking about (evening tier)
* starting something like [[RAISE]]; see [[There is room for something like RAISE]] (big chunk)
+
* understand Vanessa Kosoy's research agenda and figure out if it seems good and whether i can contribute to it
 +
* there are a lot of blog posts that I could catch up on (evening tier)
  
==Personal reflection==
+
==Technical AI safety==
 
 
* reflection post about getting involved with AI safety (big chunk)
 
 
 
==Philosophy==
 
 
 
* human values/[[deliberation]] (big chunk)
 
 
 
==Learn stuff==
 
  
* learn more machine learning so I can better follow some discussions (big chunk)
+
* I still don't feel motivated to do this since I don't feel convinced by any existing worldview/visualization that has been put forth (by e.g. MIRI or Paul) (vacation tier)
* learn more economics. I somewhat often feel confused about how to think about various AI strategy questions (e.g. history of growth, how AI systems might cooperate and increase economies of scale, what percentage of GDP might be used for computing costs) and I suspect part of the reason is that I don't know enough economics. (big chunk)
 
* understand the [[neuromorphic AI]] pathways that people like [[Steve Byrnes]] and [[gwern]] have been talking about (small chunk)
 
* there are a lot of blog posts that I could catch up on (small chunk)
 
  
 
==See also==
 
==See also==

Latest revision as of 14:25, 4 February 2022

(November 2020)

evening tier = I can make useful/meaningful progress within one hour and even when I am somewhat tired from having done other stuff during the day (at the limit, think of things like Duolingo where each task can be accomplished in a few seconds). This doesn't mean I can complete a task within one hour; completion may require several evenings. But at least a single evening can make progress in a way that doesn't require "re-doing" the same step (because I lost whatever context I had when working on it initially), and a single evening can also make definite progress (rather than feeling lost or demotivated because it requires having good ideas and I can't generate ideas when I'm tired).

weekend tier = I can make useful progress if I make it my main thing for a single day, e.g. on a weekend day. Alternatively, I can make progress within 1-2 hours as long as I am mentally alert and feeling fine.

vacation tier = I need more than a day or two of concentrated "good" time to focus on this, either because the task itself is not clearly defined (so I need to do lots of brainstorming and thinking to figure out next steps), or because it requires keeping lots of things in my head so I cannot be context-switching with other tasks (i.e. if I work on it for a few hours, then I might get distracted by another project and forget what I was doing)

Increase activity on LessWrong

  • Ask lots of questions on LW, e.g.: (duration tier depends on question; I believe I can rush through and ask certain questions within an hour which would be evening tier or weekend tier)

Writing up my opinions

  • writing some sort of overview of my beliefs regarding AI safety. like, if i was explaining things from scratch to someone, what would that sound like? (vacation tier)
  • my current take on AI timelines (vacation tier)
  • my current take on AI takeoff (vacation tier)
  • my current take on MIRI vs Paul (vacation tier)

Personal reflection

  • reflection post about getting involved with AI safety (vacation tier)

Exposition of technical topics

AI safety wiki

  • Writing articles for AI safety wiki (some pages are evening tier or weekend tier, but thinking strategically about what to write for the wiki is vacation tier)

The Vipul Strategy

Research projects

  • continue working out AI takeoff disagreements (vacation tier)
  • continue working out MIRI vs Paul (vacation tier); e.g. read through the late 2021 MIRI conversations now that that's out
  • concrete plausible scenarios for what could happen when AGI comes around (vacation tier)
  • deep dive into human evolution to figure out what the heck it might tell us about AI takeoff/AI timelines (vacation tier)
  • comparison of AI and nukes (vacation tier)
  • think about AI polarization, using examples like COVID and climate change (vacation tier)
  • write up my understanding of people's views on whole brain emulation (vacation tier)
  • clarify my thoughts on probability of saving the world via x-risk reduction (vacation tier)
  • Philosophy

Learn stuff

  • learn more machine learning so I can better follow some discussions (weekend tier as long as I am diligent to use Anki to review partial progress)
  • learn more economics. I somewhat often feel confused about how to think about various AI strategy questions (e.g. history of growth, how AI systems might cooperate and increase economies of scale, what percentage of GDP might be used for computing costs) and I suspect part of the reason is that I don't know enough economics. (weekend tier as long as I am diligent to use Anki to review partial progress)
  • understand the neuromorphic AI pathways that people like Steve Byrnes and gwern have been talking about (evening tier)
  • understand Vanessa Kosoy's research agenda and figure out if it seems good and whether i can contribute to it
  • there are a lot of blog posts that I could catch up on (evening tier)

Technical AI safety

  • I still don't feel motivated to do this since I don't feel convinced by any existing worldview/visualization that has been put forth (by e.g. MIRI or Paul) (vacation tier)

See also