LessWrong 2.0 Reader

The actual reason why we lied in the second message was "we were in a rush and forgot." 

My recollection is we sent the same message to the majority group because:

1. Treating it different would require special-casing it and that would have taken more effort.
2. If selectors of different virtues had received a different messages, we wouldn't be able to have a properly compared their behavior.
3. [At least in my mind], this was a game/test and when playing games you lie to people in the context of the game to make things work. Alternatively, it's like how scientific experimenters mislead subjects for the sake of the study.

Predictable/Unpredictable takeoff

I think long duration is way too many syllables, and I think I have similar problems with this naming schema as Fast/Slow, but, if you were going to go with this naming schema I think just saying "short takeoff" and "long takeoff" seems about as clear ("duration" comes implied IMO)

I don't love "smooth" vs "sharp" because these words don't naturally point at what seem to me to be the key concept: the duration from the first AI capable of being transformatively useful [LW · GW] to the first system which is very qualitatively generally superhuman^[1] [LW · GW]. You can have "smooth" takeoff driven by purely scaling things up where this duration is short or nonexistent.

I'm not sure I buy the distinction mattering?

Here's a few worlds:

1. Smooth takeoff to superintelligence via scaling the whole way, no RSI
2. Smooth takeoff to superintelligence via a mix of scaling, algorithmic advance, RSI, etc
3. smoothish looking takeoff via scaling (like we currently see) but then suddenly the shape of the curve changes dramatically due to RSI or similar
4. smoothish looking takeoff via scaling like we see, but, and then RSI is the mechanism by which the curve continues, but not very quickly (maybe this implies the curve actively levels off S-curve style before eventually picking up again)
5. alt-world where we weren't even seeing similar types of smoothly advancing AI, and then there's abrupt RSI takeoff in days or months
6. alt-world where we weren't seeing similar smooth scaling AI, and then RSI is the thing that initiates our current level of growth

At least with the previous way I'd been thinking about things, I think the worlds above that look smooth, I feel like "yep, that was a smooth takeoff."

Or, okay, I thought about it a bit more and maybe agree that "time between first transformatively-useful to superintelligence" is a key variable. But, I also think that variable is captured by saying "smooth takeoff/long timelines?" (which is approximately what people are currently saying?

Hmm, I updated towards being less confident while thinking about this.

Of course, you could argue that a bijection class of sets is there to formalize the notion of a quantity that generalizes to infinite sets.

Indeed, 2 sets like (1,2,3) and (A,B,C) have the same cardinality, which is 3, and cardinality is IMO the generalization of quantities to infinite sets like the real numbers. Indeed, 2 sets have the same cardinality if and only if they have a bijection.

That said, cardinality is a very coarse-grained way to look at quantities, as the Turing Machine computable sets and all arithmetical sets, which include Turing uncomputable sets, are both countable:

https://en.m.wikipedia.org/wiki/Cardinal_number

Long/short takeoff

I opted in but didn't get to play. Glad to see that it looks like people had fun! Happy Petrov Day!

Long duration/short duration takeoff

I don't love "smooth" vs "sharp" because these words don't naturally point at what seem to me to be the key concept: the duration from the first AI capable of being transformatively useful [LW · GW] to the first system which is very qualitatively generally superhuman^[1]. You can have "smooth" takeoff driven by purely scaling things up where this duration is short or nonexistent.

I also care a lot about the duration from AIs which are capable enough to 3x R&D labor to AIs which are capable enough to strictly dominate (and thus obsolete) top human scientists but which aren't necessarly very smarter. (I also care some about the duration between a bunch of different milestones and I'm not sure that my operationalizations of the milestones is the best one.)

Paul originally operationalized [LW · GW] this as seeing an economic doubling over 4 years prior to a doubling within a year, but I'd prefer for now to talk about qualitative level of capabilities rather than also entangling questions about how AI will effect the world^[2].

So, I'm tempted by "long duration" vs "short duration" takeoff, though this is pretty clumsy.

Really, there are bunch of different distinctions we care about with respect to takeoff and the progress of AI capabilities:

• As discussed above, the duration from the first transformatively useful AIs to AIs which are generally superhuman. (And between very useful AIs to top human scientist level AIs.)
• The duration from huge impacts in the world from AI (e.g. much higher GDP growth) to very superhuman AIs. This is like the above, but also folding in economic effects and other effects on the world at large which could come apart from AI capabilities even if there is a long duration takeoff in terms of capabilities.
• Software only singularity. How much the singularity is downstream of AIs working on hardware (and energy) vs just software. (Or if something well described as a singularity even happens.)
• Smoothness of AI progress vs jumpyness. As in, is progress driven by a larger number of smaller innovations and/or continuous scale ups rather being substantially driven by a small number of innovations and/or large phase changes that emerge with scale.
• Predictability of AI progress. Even if AI progress is smooth in the sense of the prior bullet, it may not follow a very predictable trend if the rate of innovations or scaling varies a lot.
• Tunability of AI capability. Is is possible to get a fully sweep of models which continuously interpolates over a range of capabilities?^[3]

Of course, these properties are quite correlated. For instance, if the relevant durations for the first bullet are very short, then I also don't expect economic impacts until AIs are much smarter. And, if the singularity requires AIs working on increasing available hardware (software only doesn't work or doesn't go very far), then you expect more economic impact and more delay.

I’ve read that OpenAI and DeepMind are hiring for multi-agent reasoning teams. I can imagine that gives another source of scaling.

I figure things like Amdahl’s law / communication overhead impose some limits there, but MCTS could probably find useful ways to divide the reasoning work and have the agents communicating at least at human level efficiency.

Continuous/Discontinuous takeoff