Future planning - Revision history

Issa at 18:53, 7 September 2020

2020-09-07T18:53:44Z

Issa at 01:26, 10 March 2020

2020-03-10T01:26:37Z

Issa at 08:06, 24 February 2020

2020-02-24T08:06:28Z

Issa at 08:05, 24 February 2020

2020-02-24T08:05:00Z

Issa at 08:02, 24 February 2020

2020-02-24T08:02:02Z

Issa at 07:51, 24 February 2020

2020-02-24T07:51:09Z

Issa: Issa moved page AI safety to Future planning without leaving a redirect

2020-02-24T07:48:32Z

Issa moved page AI safety to Future planning without leaving a redirect

Issa at 07:47, 24 February 2020

2020-02-24T07:47:38Z

Issa at 07:46, 24 February 2020

2020-02-24T07:46:14Z

Issa at 23:19, 23 February 2020

2020-02-23T23:19:30Z

@@ Line 20: / Line 20: @@
 |-
 | Paul's end of world || AGI || ? || || || 20 years? || [[AI prepping]]???
 |-
 | Great Stagnation (world stays basically the same for the next 100 years) ||

@@ Line 2: / Line 2: @@
 ** AI safety vs something else? right now AI safety seems like the best candidate for the biggest/soonest change, but i want to investigate some other things.
 ** if AI safety, then what technical agenda seems best? this matters for (1) deciding what to do technical research on, if at all; (2) what technical research to pay attention to/support.
-** if AI safety, then what will the end of the world look like (basically this is takeoff speeds + what the most likely failure mode looks like)? (this matters for prepping)
+** if AI safety, then what will the end of the world look like (basically this is takeoff speeds + what the most likely failure mode looks like)? (this matters for [[AI prepping|prepping]])
 ** how likely is the end of the world?
 ** when will AGI come?
@@ Line 19: / Line 19: @@
 | Age of em || WBE ||
 |-
-| Paul's end of world || AGI || ? || || || 20 years? || AI prepping???
+| Paul's end of world || AGI || ? || || || 20 years? || [[AI prepping]]???
 |-
 | Great Stagnation (world stays basically the same for the next 100 years) ||

@@ Line 21: / Line 21: @@
 | Paul's end of world || AGI || ? || || || 20 years? || AI prepping???
 |-
-| Great Stagnation? ||
+| Great Stagnation (world stays basically the same for the next 100 years) ||
 |-
 | Super long AI timelines (AI won't come for 100 years) ||
 |}

@@ Line 19: / Line 19: @@
 | Age of em || WBE ||
 |-
-| Paul's end of world || AGI || ? ||
+| Paul's end of world || AGI || ? || || || 20 years? || AI prepping???
 |-
 | Great Stagnation? ||

← Older revision		Revision as of 08:02, 24 February 2020
Line 1:		Line 1:
−	~~things to talk about:~~
−
	* the most decision-relevant questions for me right now (everything else should feed into one of these questions):		* the most decision-relevant questions for me right now (everything else should feed into one of these questions):
	** AI safety vs something else? right now AI safety seems like the best candidate for the biggest/soonest change, but i want to investigate some other things.		** AI safety vs something else? right now AI safety seems like the best candidate for the biggest/soonest change, but i want to investigate some other things.

@@ Line 13: / Line 13: @@
 ! Name of scenario !! Next big thing? !! AI safety technical agenda !! What will end of the world look like? !! How likely is the world to end? !! When will the world end/reach a singularity/cure aging? || What I should do
 |-
-| Eliezerian end of world || AGI || MIRI || FOOM/AI takeover || Highly likely? || 10-20 years? || Don't have kids. Probably don't even bother with wife search. Focus on AI safety research, either field building or figuring out how to contribute to MIRI-like technical work.
+| Eliezerian end of world || AGI || MIRI? || FOOM/AI takeover || Highly likely? || 10-20 years? || Don't have kids. Probably don't even bother with wife search. Focus on AI safety research, either field building or figuring out how to contribute to MIRI-like technical work.
 |-
+| Eliezerian end of world, but longer timelines || AGI || MIRI? || FOOM/AI takeover || Highly likely? || 40 years ||
 |}

← Older revision	Revision as of 07:48, 24 February 2020
(No difference)

← Older revision		Revision as of 07:46, 24 February 2020
Line 7:		Line 7:
	** how likely is the end of the world?		** how likely is the end of the world?
	** when will AGI come?		** when will AGI come?
		+
		+	Example scenarios:
		+
		+	{\| class="wikitable"
		+	! Name of scenario !! Next big thing? !! AI safety technical agenda !! What will end of the world look like? !! How likely is the world to end? !! When will the world end/reach a singularity/cure aging?
		+	\|-
		+	\| Eliezerian end of world \|\| AGI \|\| MIRI \|\| FOOM/AI takeover \|\| Highly likely? \|\| 10-20 years?
		+	\|-
		+	\|
		+	\|}

← Older revision		Revision as of 23:19, 23 February 2020
Line 7:		Line 7:
	** how likely is the end of the world?		** how likely is the end of the world?
	** when will AGI come?		** when will AGI come?
−	* list of things people disagree about:<ref>[https://drive.google.com/file/d/1wI21XP-lRa6mi5h0dq_USooz0LpysdhS/view Clarifying some key hypotheses in AI alignment].</ref>
−	** how doomed ML safety approaches are e.g. see discussion [https://www.greaterwrong.com/posts/suxvE2ddnYMPJN9HD/realism-about-rationality#comment-32dCL2u6p8L8td9BA here] -- [[How doomed are ML safety approaches?]]
−	*** there's the sort of opposite question of, how doomed is MIRI's approach? i.e. if there turns out to be no [[simple core algorithm for agency]], or if understanding agency better doesn't help us build an AGI, then we might not be in a better place wrt aligning AI.
−	** can MIRI-type research be done in time to help with AGI? see [https://www.greaterwrong.com/posts/suxvE2ddnYMPJN9HD/realism-about-rationality#comment-Dk5LmWMEL55ufkTB5 this comment]
−	** prior on difficulty of alignment, and ideas like "if ML-based safety were to have any shot at working, wouldn't we just go all the way and expect the default (no EA intervention) approach to AGI to just produce basically ok outcomes?"
−	** probability of doom
−	** civilizational adequacy
−	** probability of doom without any special EA intervention
−	** shape of takeoff
−	*** [[Will there be significant changes to the world prior to some critical AI capability threshold being reached?]]
−	** what precursors/narrow systems we will see prior to AGI
−	** AI timelines
−	** what the first AGI will look like
−	** how big of a problem collusion between subsystems of an AI will be
−	** how likely optimization daemons/mesa-optimizers are or what they will look like
−	** whether there is a basin of attraction for corrigibility
−	** something-like-realism-about-rationality, e.g. "Is there a theory of rationality that is sufficiently precise to build hierarchies of abstraction?" [https://www.greaterwrong.com/posts/suxvE2ddnYMPJN9HD/realism-about-rationality#comment-YMNwHcPNPd4pDK7MR]
−	** whether MIRI-type work can be done in time
−	** whether ML-based approaches are doomed
−	** whether "weird recursions" are a good idea
−	** whether we can correct mistakes when deploying AI systems as they come up (i.e. how catastrophic the initial problems will be)
−	** how many/how "lumpy" insights are for creating an AGI
−	*** "the degree of complexity of useful combination, and the degree to which a simple general architecture search and generation process can find such useful combinations for particular tasks" [https://www.facebook.com/yudkowsky/posts/10155848910529228?comment_id=10155848951264228&reply_comment_id=10155849315174228]
−	** how much sharing/trading there will be between different AI companies (eliezer vs [[Robin Hanson]]) -- this one is downstream of lumpiness of insights, because hanson expects that if there are very few insights needed to get to AGI, then there won't be any need for sharing (so in that case even hanson would agree with eliezer).
−	** how important it is to get the right architecture e.g. "That is what I meant by suggesting that architecture isn’t the key to AGI." [https://www.greaterwrong.com/posts/D3NspiH2nhKA6B2PE/what-evidence-is-alphago-zero-re-agi-complexity]. There is [[Dario Amodei]]'s comment [https://www.facebook.com/yudkowsky/posts/10155848910529228?comment_id=10155849004324228&reply_comment_id=10155849068769228 here] which is the opposite view.
−	** is it possible to turn a small lead in AGI development into a big lead?
−	** will AGI be agent-like?
−	** whether an AGI will look like a utility maximizer?
−	** will AGI appear rational to humans? (efficient relative to humans)
−	** will current ML techniques scale to AGI?
−	** will there be small-scale AI failures prior to the end of the world?
−	** will failure be conspicuous?
−	** how likely is a treacherous turn/context change type of failure?
−	** how much overlap is there between AI capabilities work and safety work? (e.g. is it reasonable to say things like "making progress on safety requires advancing capabilities"?)
−	** what will failure look like? yudkowskian takeover vs paul's "we get what we measure, and our ability to get what we specify outstrips our ability to measure what we truly want" vs paul's influence-seeking optimizers/daemons vs ...
−	** how strong of a guarantee do we need for the safety of AI? proof-level (does anyone actually argue this?) vs security mindset vs whatever ML safety people believe
−	** deep insights needed to build an ''aligned'' AGI? see also [[Different senses of claims about AGI]] i.e. it might not require deep insights to build any old AGI, but still require deep insights for an aligned one.
−	** how useful is each kind of research e.g. Paul's vs MIRI's?
−	** what lessons can we learn by looking at the [[Evolution\|evolutionary history]] of chimps vs humans?
−	** what lessons can we learn from [[AlphaGo]]?
−	** is [[prosaic AI]] possible? see [https://srconstantin.wordpress.com/2017/02/21/strong-ai-isnt-here-yet/] for a post arguing against.
−	** how short is the window between "clearly infrahuman" and "clearly superhuman" for important real-world tasks like "doing AI research"?
−
−	~~==References==~~
−
−	~~<references/>~~