michael_dello

Sen­tience In­sti­tute 2023 End of Year Summary

• michael_dello 9 Jun 2023 1:02 UTC

  1 point

  0

  on: Sen­tience matters

  Brave New World comes to mind. I’ve often been a little confused when people say creating people who are happy with their role in life is a dystopia when that sounds like the goal to me. Creating sentient minds that are happy with their life seems much better than creating them randomly.

Job list­ing (closed): Sen­tience In­sti­tute is ac­cept­ing ap­pli­ca­tions for a researcher

• michael_dello 2 Mar 2023 4:21 UTC

  2 points

  0

  on: Don’t Jump or I’ll...

  I really enjoyed this, but to be honest I didn’t understand the part about the models. I’m not sure if there was a message I should take on board there or if it was just for fun.

  I have thought about a little about the dynamics of “I’ll do a bad thing if you do a bad thing”. When I was trying to stop myself from engaging in a habit I was trying to cut out, I promised myself I’d donate $10 to Donald Trump’s election campaign (bad, from my perspective) each time I did the thing. I never did, but I wonder if I would have if it cam to it. I think maybe yes I would/​should have, because then that would really make me not want to do the thing again. In this case I’m representing both actors in the above short story, and convincing myself I’d follow through.

  Another time I was trying to stop drinking alcohol to save money, and promised myself I’d donate $10 to a good charity every night I was out but didn’t drink. This worked really well—I was net saving money and also donating money to good causes.

  In both of these cases, I had no public accountability. I have taken a public giving pledge and posted it on my website, which gives me some accountability, though I guess the only cost to not following through on this is a hit to my credibility(?).

• michael_dello 2 Mar 2023 4:17 UTC

  2 points

  0

  on: Bing Chat is blatantly, ag­gres­sively misaligned

  The weirdest thing I was able to get Bing Chat to do was:

  I had it write a short story, and halfway through writing it, it deleted what it has written so far (several hundred words) and said it didn’t want to talk about this topic anymore. I’m not sure if it accidentally hit some kind of trigger for a taboo topic. Unfortunately I wasn’t reading as it went so am not sure what happened. I haven’t been able to recreate this.

• michael_dello 15 Feb 2023 1:57 UTC

  1 point

  0

  in reply to: jefftk’s comment on: Duck­bill Masks Are Great

  Thanks! Do you have any particular strategy behind your reuse? I have a few bags I rotate by putting masks in, and leaving at least 10 days between when I put the last mask in a bag to when I start using ones from that bag again.

• michael_dello 8 Feb 2023 4:58 UTC

  1 point

  0

  on: Duck­bill Masks Are Great

  Thanks for sharing, I hadn’t seen these before and will try them. Do you reuse them?

  To latch on to something else from your post, it’s interesting to hear some people observe that they have more trouble breathing with some masks than others, or with masks than no masks, while others don’t. Personally, I haven’t noticed any difference, and do a lot of sporting activities (bouldering, jogging 10km) with a mask without feeling like it makes a difference.

• michael_dello 1 Feb 2023 3:00 UTC

  12 points

  0

  on: Nice Clothes are Good, Actually

  Because dressing nice makes your vibes better and people treat you better and are more willing to accommodate your requests.

  This is probably the part of the case for dressing nicely I find compelling, but to be fair it’s a big one. Beyond this and signalling, what other reasons are there that people wear nice/​expensive clothes?

  Anecdotally, the one time I wore a blazer for a flight (because I heard that you’re more likely to be bumped to business class), a stranger asked me if I’d like to be their free plus one for their airlines’ lounge. Relatedly, I’ll be flying for the first time since getting my PhD in a few months. I’ve heard that doctors get treated better by airlines (maybe because they assume they are all medical doctors and would be useful in an emergency?). I see my ‘Dr’ title in a similar lens as nice clothes. I don’t really care much about it, but it can be useful and help me achieve my goals, so I should probably get over my mild discomfort with seeming a bit ‘wanky’ by using my title. I’ve already noticed that people think you’re smarter about things unrelated to your research just because you’re doing a PhD.

• michael_dello 27 Jan 2023 0:45 UTC

  1 point

  in reply to: Alex Flint’s comment on: Agency in Con­way’s Game of Life

  It surprises me a little that there hasn’t been more work on working backwards in Life. Perhaps it’s just too hard/​not useful given the number of possible X-1 time slices.

  With the smiley face example, there could be a very large number of combinations for the squares outside the smiley face at X-1 which result in the same empty grid space (i.e. many possible self-destructing patterns).

  I’m unreasonably fond of brute forcing problems like these. I don’t know if I’d have anything useful to say on this topic that I haven’t already, but I’m interested to follow this work. I think this is a fascinating analogy for the control problem.

  Edit—It just occurred to me, thanks to a friend, that instead of reverse engineering the desired state, it might be easier to just randomise the inputs until you get the outcome you want (not sure why this didn’t occur to me). Still very intensive, but perhaps easier.

• michael_dello 27 Jan 2023 0:26 UTC

  1 point

  in reply to: gwern’s comment on: Agency in Con­way’s Game of Life

  That’s true, but would I be right in saying that as long as there are no Garden of Eden states, you could in theory at least generate one possible prior state?

• michael_dello 26 Jan 2023 3:44 UTC

  3 points

  on: Agency in Con­way’s Game of Life

  I really enjoyed this read, thanks. I’m an enjoyer of Life from afar so there may be a trivial answer to this question.

  Is it possible to reverse engineer a state in Life? E.g., for time state X, can you easily determine a possible time state X-1? I know that multiple X-1 time states can lead to the same X time state, but is it possible to generate one? Can you reverse engineer any possible X-100 time state for a given time state X? I ask because I wonder if you could generate an X-(10^60) time state on a 10^30 by 10^30 grid where time state X is a large smiley face.

  This almost certainly wouldn’t give you a 10^20 by 10^20 corner that generates a smiley face for all or even a small fraction of iterations of the rest of the grid. But perhaps you could randomise the reverse engineering and keep generating X-(10^60) states until you get one that creates a smiley face for the greatest number of 10^30 by 10^30 states (randomly generating that part of the grid and running it for 10^60 steps), then call that your solution to the control problem

  I used the numbers from your example in mine, but perhaps one could demonstrate this with a much smaller grid. Say for example, a 10^2 by 10^2 grid with 10^5 time steps, and reverse engineer a smiley face.

  This might be a way of brute forcing the control problem, so to speak. Proving it is possible in a smaller grid might show it’s possible with larger grids.

• michael_dello 26 Jan 2023 2:25 UTC

  1 point

  0

  on: When Did EA Start?

  This is cool! I came across EA in early 2015, and I’ve sometimes been curious about what happened in the years before then. Books like The Most Good You Can Do sometimes incidentally give anecdotes, but I haven’t seen a complete picture in one public place. Not to toot our own horn too much, but I wonder if there will one day be a documentary about the movement itself, and how positive it would be (easy to paint EA as a cult, for example).

• michael_dello 24 Jan 2023 6:29 UTC

  2 points

  0

  on: Movie Re­view: Megan

  Thanks for writing this! I also wrote the movie off after seeing the trailer, but will give it a go based on this review.

  “After Cady shows interest, Gemma builds the AI robot doll, Megan, to serve as Cady’s companion and toy. At home. In a week.” Is there a name for this trope? I can’t stand it, and I struggle to suspend my disbelief after lazy writing mistakes like this.

• michael_dello 28 Dec 2022 0:43 UTC

  1 point

  0

  on: Slightly against al­ign­ing with neo-luddites

  I haven’t spent much time thinking about this at all, but it’s interesting to think about the speed with which regulation gets put into place for environmental issues such as climate change and HFC’s ban to test how likely it is that regulation will be put in place in time to meaningfully slow down AI.

  These aren’t perfectly analogous since AI going wrong would likely be much worse than the worst case climate change scenarios, but the amount of time it takes to get climate regulation makes me pessimistic. However, HFC’s were banned relatively quickly after realising the problem, so maybe there is some hope.

• michael_dello 27 Dec 2022 3:10 UTC

  4 points

  on: What 2026 looks like (Daniel’s Me­dian Fu­ture)

  “Most stories are written backwards. The author begins with some idea of how it will end, and arranges the story to achieve that ending. Reality, by contrast, proceeds from past to future. It isn’t trying to entertain anyone or prove a point in an argument.”

  This seems to me like the most important takeaway for writing stories that are useful for thinking about the future. Sci-fi is great for thinking about possible future scenarios, but it’s usually written for entertainment value, not predictive value, and so tends to start with an entertaining ‘end’ or plot in mind, and works backwards from there to an extent.

• michael_dello 10 Apr 2022 22:20 UTC

  21 points

  in reply to: Nathan Helm-Burger’s comment on: A con­crete bet offer to those with short AI timelines

  Shouldn’t it be: ‘They pay you $1,000 now, and in 3 years, you pay them back plus $3,000’ (as per Bryan Caplan’s discussion in the latest 80k podcast episode)? The money won’t do anyone much good if they receive in it a FOOM scenario.

• michael_dello 14 May 2020 1:44 UTC

  1 point

  on: What work of fic­tion ex­plore in­creased trans­parency in the world?

  It’s more of a backdrop than a key focus, but the Culture series by Iain Banks features a civilisation where AI minds can monitor everything on their spaceships and habitats to near perfection. The only thing they choose not to monitor (usually), despite being able to is the thoughts of biological lifeforms.

• michael_dello 12 May 2020 6:33 UTC

  1 point

  on: Availability

  ″ While building dams decreases the frequency of floods, damage per flood is afterward so much greater that average yearly damage increases. ”

  This is fascinating. Should we not be building dams? Could we say the same thing about fighting bushfires, since fighting them increases the amount of fuel they have available for next time?

• michael_dello 6 May 2020 22:22 UTC

  1 point

  on: Why truth? And...

  Regarding the Spock probability reference, I’ve always imagined that TV shows and movies either take place in the parallel universe where very specific events happen to take place (e.g. the universe where the ‘bad guys’ miss the ‘good guys’ with all of their bullets despite being trained soldiers), or in the case of the Enterprise, the camera follows the adventures of the one ship that is super lucky. Perhaps the probability of survival really is 2.234 %, the Enterprise is just the 1 in 1,000 ship that keeps surviving (because who wants the camera to follow those other ships?).

• michael_dello 10 Oct 2015 4:02 UTC

  0 points

  on: Another Cri­tique of Effec­tive Altruism

  “Why haven’t more EAs signed up for a course on global security, or tried to understand how DARPA funds projects, or learned about third-world health?”

  A very interesting point, and you’ve inspired me to take such a course. Does anyone have any recommendations for a good (and preferable reputable, given our credential addicted world) course relating to global security and health?