All of Morpheus's Comments + Replies

TLDR: Recent B.S. Computer Science Graduate. Seeking opportunities. Looking for roles to widen my skillset (for example through a role in operations). Open to roles that build upon my current skill set or that expand my skills in operations or technical writing. Interested in reducing xrisk through technical or policy work on AI or biorisk.

Skills & background: General Math and Programming skills. Participated in John Wentworth's SERIMATS online stream for technical AI alignment in 2023. I know how to use python, pandas, matplotlib and pytorch. I coorga... (read more)

Not really. The perfusion techniques haven't really updated in decades.

Honestly, not knowledgeable enough to know how much of a qualitative difference that makes (eg. how much does that increase your expected value of future you?).

They might also improve the process somewhat, but at the current scope, the impact is very limited as long as there is like less than (~10,000?) (just a ballpark, not looking up actual number) people signed up, and the whole thing costs ~50,000$ if you are getting it real cheap. Like, I also have extended family members that a... (read more)

I do not see the difference in those dying of other causes also being a tragedy. Even if you do believe extending the human lifespan is not important, consider the alternative case where you’re wrong.

I think most EAs would agree that death is bad. The important question would be how tractable life expansion is.

This is related to Life Extension, but even more neglected, and probably even more impactful. The number of people actually working on cryonics to improve human minds is easily below 100. A key advancement from one individual in research, techno

... (read more)
2
Prometheus
1y
"Also, the limiting factor for cryonics seems to be more it's weirdness rather than research?"   Not really. The perfusion techniques haven't really updated in decades. And the standby teams to actually perform preservation in the event of an accident are extremely spread out and limited. I think some new organizations need to breath life back into cryonics, with clear benchmarks for standards they hope to achieve over a certain timeline. I think Tomorrow Biostasis is doing the kind of thing I'm speaking of, but would love to see more organizations like them.

This might come as the biggest surprise to be on the list. After all, space exploration is expensive and difficult. But there are very few out there who are actually working on how to change humanity from being a Single Point of Failure System. If we are serious about longtermism and truly decreasing x-risk, this might be one of the most crucial achievements needed. Any x-risk is most likely greatly reduced by this, even perhaps AGI*. The sooner this process begins, the greater the reduction in risk, since this will be a very slow process.

Seems not eve... (read more)

I was also confused about why no one has written something more extensive on nanotech. My guess would be that, it might be rather hard to have a catastrophe 'by accident' as the gray goo failure mode is rather obviously undesirable. From the Wikipedia article on gray goo I gathered that Erik Drexler thinks it's totally possible to develop safe nanotechnology. That distinguishes it from AI which he seems to have shifted his focus to. See also this report, I found through this question

2
Prometheus
1y
My guess a big reason is there doesn't really seem to be any framework to go about working on it, except perhaps on the policy side. Testing out various forms of nanotechnology to see if they're dangerous might be very bad. Even hypothetically doing that might create information hazards. I imagine we would have to see a few daring EAs blaze the trail for others to follow in. There's also the obvious skill and knowledge gap. You can't easily jump into something like nanotech the way you could for something like animal welfare.

I sort of view AGI as a standin for powerful optimization capable of killing us in AI Alignment contexts.

Yeah, I think I would count these as unambigous in hindsight. Though siren Worlds might be an exception.

Do you also think this yourself? I don't clearly see what worlds look like, where P (doom | AGI) would be ambiguous in hindsight? Some mayor accident because everything is going too fast?

2
Guy Raveh
1y
There are some things we would recognize as an AGI, but others (that we're still worried about) are ambiguous. There are some things we would immediately recognize as 'doom' (like extinction) but others are more ambiguous (like those in Paul Christiano's "what failure looks like", or like a seemingly eternal dictatorship).
1
TheMcDouglas
2y
Great! (-:

Just in case this has something to do with the link: I got an error when trying to join the group with my google account. (Might try with email later).

1
Morpheus
2y
email worked

I like your comparisons with other historical cases when people thought they had inevitable theories about society, and it is a thing I think about.

I do have a pet peeve though about the following claim.

Expected values were being used by the authors inappropriately (that is, without data to inform the probability estimates).

 Let's consider a very short argument for strong longterminism (and a tractable way to influence the distant future by reducing x-risk):
- There is a lot of future ahead of us.
- The universe is large
-  humans are fragile/the un... (read more)

My new Favorite: What share of total computation did pocket calculators account for in 1986?

41%

Thank you! The most surprising (though maybe not most impactful) cards for me so far were the once on neurons:
Sure. Mammals make up the minority of neurons, but HOW ON EARTH are 90 Percent of those from humans? 

Also, 30% from fish? I would have expected fish to be negligible.

2
Pablo
3y
The content of those cards also represented the biggest update for me. I wouldn't have guessed that the truth was roughly "two third of neurons are invertebrate neurons, one third of neurons are fish neurons".
3
Morpheus
3y
My new Favorite: What share of total computation did pocket calculators account for in 1986?

I really like the idea behind this post/series. I'd already come across Lindy's Law/delta T and the rule of succession, by reading other people use it in their predictions, but I had already thought that this was a really inefficient way to learn. I skimmed a few statistics textbooks, but I did not come across a lot of techniques that I actually ended up using. 

I also liked the examples you gave. I felt like 1-3 explicit practice Problems at the end would also have been nice like:

Tesla was founded in 2003.

  • How many years from now does tesla have a 25/7
... (read more)