Max Clarke

Karma: 275

Max Clarke 26 Jan 2023 22:58 UTC
6 points
7
in reply to: Nathan Young’s comment on: Possible changes to EA, a big upvoted list
Definitely, for example if people are bikeshedding (vigorously discussing something that doesn’t matter very much)

Max Clarke 20 Jan 2023 0:52 UTC
1 point
0
in reply to: Nathan Young’s comment on: Possible changes to EA, a big upvoted list
Another proposal: Visibility karma remains 1 to 1, and agreement karma acts as a weak multiplier when either positive or negative.
So:
- A comment with [ +100 | 0 ] would have a weight of 100
- A comment with [ +100 | 0 ] but with 50✅ and 50❌ would have a weight of 100 + log10(50 + 50) = 200
- A comment with [ +100 | 100✅ ] would have a weight of say 100 * log10(✓100) = 200
- A comment with [+0 | 1000✅ ] would have a weight of 0.
Could also give karma on that basis.
However thinking about it, I think the result would be people would start using the visibility vote to express opinion even more...

Max Clarke 20 Jan 2023 0:34 UTC
1 point
0
in reply to: Nathan Young’s comment on: Possible changes to EA, a big upvoted list
Would you gift your karma if that option was available?

Max Clarke 20 Jan 2023 0:26 UTC
1 point
0
in reply to: Nathan Young’s comment on: Possible changes to EA, a big upvoted list
This is good for calibrating what the votes mean across the responses

Max Clarke 20 Jan 2023 0:20 UTC
1 point
0
in reply to: Nathan Young’s comment on: Possible changes to EA, a big upvoted list
A little ambiguous between “disagree karma & upvote karma should have equal weight” and “karma should have equal weight between people”

Max Clarke 20 Jan 2023 0:14 UTC
1 point
2
in reply to: Nathan Young’s comment on: Possible changes to EA, a big upvoted list
I think because the sorting is solely on karma, the line is “Everything above this is worth considering” / “Everything below this is not important” as opposed to “Everything above this is worth doing”

Max Clarke 20 Jan 2023 0:11 UTC
1 point
4
in reply to: Felix Wolf’s comment on: Possible changes to EA, a big upvoted list
It’s karma—which is kind of wrong here.

Max Clarke 20 Jan 2023 0:08 UTC
1 point
−1
in reply to: Coafos’s comment on: Possible changes to EA, a big upvoted list
One situation I use strong votes for is whenever I do “upvote/disagree” or “downvote/agree”. I do this to offset others who tend not to split their votes.

Max Clarke 20 Jan 2023 0:07 UTC
2 points
1
in reply to: Coafos’s comment on: Possible changes to EA, a big upvoted list
I think some kind of “strong vote income”, perhaps just a daily limit as you say, would work.

Max Clarke 13 Nov 2022 8:01 UTC
1 point
2
in reply to: EliezerYudkowsky’s comment on: A personal statement on FTX
People who read this far seem to have upvoted

Max Clarke 13 Nov 2022 7:52 UTC
1 point
0
in reply to: EliezerYudkowsky’s comment on: A personal statement on FTX
I would have expected the opposite corner of the two axis voting (because I think people don’t like the language)

Max Clarke 11 Nov 2022 4:24 UTC
3 points
0
in reply to: Chris Kerr’s comment on: Money Stuff: FTX Had a Death Spiral
seems he has ended up giving more to the democratic party than ea lol

Max Clarke 9 Nov 2022 23:59 UTC
10 points
1
on: What should I ask Joe Carlsmith — Open Phil researcher, philosopher and blogger?
There seems to be two different conceptual models for AI risk.

The first is a model like in his report “Existential risk from power-seeking AI”, in which he lays out a number of things, which, if they happen, will cause AI takeover.

The second is a model (which stems from Yudkowsky & Bosteom, and more recently in Michael Cohen’s work https://www.lesswrong.com/posts/XtBJTFszs8oP3vXic/?commentId=yqm7fHaf2qmhCRiNA ) where we should expect takeover by malign AGI by default, unless certain things happen.

I personally think the second model is much more reasonable. Do you have any rebuttal?

Max Clarke 9 Nov 2022 3:38 UTC
10 points
11
in reply to: Stuart Buck’s comment on: FTX will likely go bankrupt. What we know and some forecasts on what will happen next
Likewise, I have a post from January suggesting that crypto assets are over-represented in the EA funding portfolio.

Max Clarke 6 Nov 2022 11:29 UTC
7 points
1
in reply to: Linch’s comment on: Instead of technical research, more people should focus on buying time
Probably the number of people actually pushing the frontier of alignment is more like 30, and for capabilities maybe 3000. If the 270 remaining alignment people can influence those 3000 (biiiig if, but) then the odds aren’t that bad

Max Clarke 6 Nov 2022 5:50 UTC
5 points
2
in reply to: Emrik’s comment on: Instead of technical research, more people should focus on buying time
Thinking about

Max Clarke 6 Nov 2022 2:03 UTC
5 points
2
in reply to: Emrik’s comment on: Instead of technical research, more people should focus on buying time
Not sure what Rob is referring to but there are a fair few examples of org/people’s purposes slipping from alignment to capabilities, eg. OpenAI

I myself find it surprisingly difficult to focus on ideas that are robustly beneficial to alignment but not to capabilities.

(E.g. I have a bunch of interpretability ideas. But interpretability can only have no impact on, or accelerate timelines)

Do you know if any of the alignment orgs have some kind of alignment research NDA, with a panel to allow any alignment-only ideas be public, but keep the maybe-capabilities ideas private?

Max Clarke 6 Nov 2022 1:37 UTC
5 points
8
in reply to: Miranda_Zhang’s comment on: Instead of technical research, more people should focus on buying time
I think probably this post should be edited and “focus on low risk interventions first” put in bold in the first sentence and put right next to the pictures. Because the most careless people (possibly like me...) are the ones that will read that and not read the current caveats

Max Clarke 6 Nov 2022 1:28 UTC
2 points
0
in reply to: Max Clarke’s comment on: Instead of technical research, more people should focus on buying time
An addendum is then:
1. If Buying time interventions are conjunctive (ie. one can cancel out the effect of the others); but technical alignment is disjunctive
2. If the distribution of people performing both kinds of intervention is mostly towards the lower end of thoughtfulness/competence, (which we should imo expect)
Then technical alignment is a better recommendation for most people.

In fact it suggests that the graph in the post should be reversed (but the axis at the bottom should be social competence rather than technical competence)

Max Clarke 6 Nov 2022 1:20 UTC
8 points
4
in reply to: Miranda_Zhang’s comment on: Instead of technical research, more people should focus on buying time
Rob puts it well in his comment as “social coordination”. If someone tries “buying time” interventions and fails, I think that because of largely social effects, poorly done “buying time” interventions have potential to both fail at buying time and preclude further coordination with mainstream ML. So net negative effect.

On the other hand, technical alignment does not have this risk.

I agree that technical alignment has the risk of accelerating timelines though.

But if someone tries technical alignment and fails to produce results, that has no impact compared to a counterfactual where they just did web dev or something.

My reference point here is the anecdotal disdain (from Twitter, YouTube, can dm if you want) some in the ML community have for anyone who they perceive to be slowing them down.