MichaelDickens

Karma: 1,886

MichaelDickens 3 Dec 2025 13:57 UTC
2 points
2
in reply to: niplav’s comment on: Charlie Steiner’s Shortform
My guess is you’re the only person in the world who does this, but also this is better than what everyone else is doing and maybe I should start doing it

MichaelDickens 30 Nov 2025 16:54 UTC
2 points
0
on: Ben’s 10 Tips for Event Feedback Forms

Also, sometimes people let you know some important reason why you shouldn’t count their datapoint. For example, someone might rate the food ¹⁄₁₀, which sounds terrible, but then they’ll clarify that they weren’t there during mealtimes and didn’t eat the food, and just gave it ¹⁄₁₀ because it was mandatory! This is rarely predictable, but especially with autistic people you occasionally get odd edge-cases like this.

My autistic friend would like to know: if there’s a mandatory question to rate the food but he didn’t eat it, which number should he pick?

MichaelDickens 30 Nov 2025 16:52 UTC
2 points
0
in reply to: sjadler’s comment on: Quinn’s Shortform
Or maybe I’m the one who’s been misunderstanding it! I don’t think I have a great understanding of the term tbh so you’re probably right.

If that’s what it means then instead of “Bayes points”, Quinn could call it “credibility” or “predictive accuracy” or something.

MichaelDickens 30 Nov 2025 0:26 UTC
4 points
0
in reply to: kave’s comment on: Where I Am Donating in 2025
Thanks, I didn’t see the page on how matching works. I edited that section to fix it.

My first draft actually said something more accurate, but then I edited it to be worse :/ I have edited it back to say something more like the original version.

MichaelDickens 30 Nov 2025 0:08 UTC
2 points
0
in reply to: Dagon’s comment on: Quinn’s Shortform
I think the term means something like “you demonstrated truth-seeking character/virtue”.

Example: Someone (I forget who it was, sorry) came up with a novel AI alignment theory, and then they wrote a long post about how their own theory was deeply flawed. That post earned them Bayes points.

MichaelDickens 29 Nov 2025 4:52 UTC
3 points
0
on: Claude Opus 4.5: Model Card, Alignment and Safety

In terms of surviving superintelligence, it’s still the scene from The Phantom Menace. As in, that won’t be enough.

Are you talking about the scene near the beginning where the Neimoidians send some battle droids to kill the Jedi and all the droids die in 4.5 seconds flat?

Edit: I looked up the script and I was close but not quite right. “That won’t be enough” is a line spoken by one of the Neimoidians after locking the doors to the bridge to keep the Jedi out. Qui-Gon was poised to cut through the door in 4.5 seconds flat until they closed the blast doors.

MichaelDickens 28 Nov 2025 15:52 UTC
4 points
0
in reply to: mishka’s comment on: We won’t solve non-alignment problems by doing research
Good callout. I was glad to hear that Ilya is thinking about all sentient life and not just humans.

I didn’t interpret it to mean that he’s working on thing 1. The direct quote was

I think in particular, there’s a case to be made that it will be easier to build an AI that cares about sentient life than an AI that cares about human life alone, because the AI itself will be sentient. And if you think about things like mirror neurons and human empathy for animals, which you might argue it’s not big enough, but it exists. I think it’s an emergent property from the fact that we model others with the same circuit that we use to model ourselves, because that’s the most efficient thing to do.

Sounds to me like he expects an aligned AI to care about all sentient beings, but he isn’t necessarily working on making that happen. AFAIK Ilya’s new venture hasn’t published any alignment research yet, so we don’t know what exactly he’s working on.

MichaelDickens 26 Nov 2025 21:24 UTC
2 points
0
in reply to: Oksana_Kot’s comment on: We won’t solve non-alignment problems by doing research
The problem of coordinating on AI development isn’t the same thing as solving the alignment problem, but it’s not the thing I’m pointing at in this post because it’s still about avoiding misalignment.

MichaelDickens 24 Nov 2025 19:48 UTC
6 points
0
in reply to: Mitchell_Porter’s comment on: We won’t solve non-alignment problems by doing research
I plan on writing something longer about this in the future but people use “alignment” to refer to two different things, basically thing 1 is “ASI solves ethics and then behaves ethically” and thing 2 is “ASI does what people want it to do”. Approximately nobody is working on thing 1, only on thing 2, and thing 2 doesn’t get us a solution to non-alignment problems.

MichaelDickens 20 Nov 2025 4:54 UTC
11 points
0
on: What Is The Basin Of Convergence For Kelly Betting?
For constant-relative-risk-aversion (CRRA) utility functions, the Kelly criterion is optimal iff you have logarithmic utility. For proof, see Samuelson (1971), The “Fallacy” of Maximizing the Geometric Mean in Long Sequences of Investing or Gambling.

I think there is only a fixed-proportion betting rule (i.e. “bet P% of your bankroll” for fixed P) for CRRA utility functions, because if risk aversion varies then the betting rule must also vary. But I’m not sure how to prove that.

ETA: Actually I think it shouldn’t be too hard to prove that using the definition of CRRA. You could do something like, assume a fixed-proportion betting rule exists for some constant P, and then calculate the implied relative risk aversion and show that it must be a constant.

MichaelDickens 19 Nov 2025 19:43 UTC
4 points
0
in reply to: One’s comment on: Hastings’s Shortform
There is a harder second-order question of “what sorts of videos maximize watch time, and will those be bad for my child?” Hastings’s evidence points toward “yes”, but I don’t think the answer is obvious a priori. (The things YouTube thinks I want to watch are almost all good or neutral for me; YMMV.)

MichaelDickens 19 Nov 2025 15:22 UTC
2 points
0
in reply to: casens’s comment on: Knowing Whether AI Alignment Is a One-Shot Problem Is a One-Shot Problem
Oops! Fixed.

MichaelDickens 18 Nov 2025 18:19 UTC
2 points
0
on: Your Clone Wants to Kill You Because You Assumed Too Much
For posterity, I would just like to make it clear that if I were ever cloned, I would treat my clone as an equal, and I wouldn’t make him do things I wouldn’t do—in fact I wouldn’t try to make him do anything at all, we’d make decisions jointly.

(But of course my clone would already know that, because he’s me.)

(I’ve spent an unreasonable amount of time thinking about how to devise a fair decision procedure between me and my clone to allocate tasks and resources in a perfectly egalitarian way.)

MichaelDickens 16 Nov 2025 20:20 UTC
4 points
0
in reply to: RationalElf’s comment on: GradientDissenter’s Shortform
FWIW I think Habryka was right to call out that some parts of my comment were bad, and the scolding got me to think more carefully about it.

MichaelDickens 16 Nov 2025 18:43 UTC
2 points
2
in reply to: Brendan Long’s comment on: Brendan Long’s Shortform
Are you also lifting weights? I’m quite confident that you can gain muscle while taking retatrutide if you lift weights.

IIRC GLP-1 agonists cause more muscle loss than “old-fashioned” dieting, but the effect of resistance training far outweighs the extra muscle loss.

MichaelDickens 16 Nov 2025 18:38 UTC
5 points
2
in reply to: Adam Scholl’s comment on: AI safety undervalues founders
My question is, how do you make AI risk known while minimizing the risk of paradoxical impacts? “Never talk about it” is the wrong answer, but I expect there’s a way to do better than we’ve done so far. This seems like an important thing to try to understand.

MichaelDickens 15 Nov 2025 20:46 UTC
2 points
0
in reply to: Tapatakt’s comment on: Tapatakt’s Shortform
I don’t do this on purpose but I feel like 90% of what I write about AI is something Eliezer already said at some point.

MichaelDickens 15 Nov 2025 6:08 UTC
5 points
2
in reply to: habryka’s comment on: GradientDissenter’s Shortform
Yeah I pretty much agree with what you’re saying. But I think I misunderstood your comment before mine, and the thing you’re talking about was not captured by the model I wrote in my last comment; so I have some more thinking to do.

I didn’t mean “can be trusted to take AI risk seriously” as “indeterminate trustworthiness but cares about x-risk”, more like “the conjunction of trustworthy + cares about x-risk”.

MichaelDickens 15 Nov 2025 5:32 UTC
4 points
0
in reply to: habryka’s comment on: GradientDissenter’s Shortform
ETA: I think this comment is missing some important things and I endorse Habryka’s reply more than I endorse this comment

Like, the most important thing to estimate when evaluating a political candidate is their trustworthiness and integrity! It’s the thing that would flip the sign on whether supporting someone is good or bad for the world.

I agree that this is an important thing that deserved more consideration in Eric’s analysis (I wrote a note about it on Oct 22 but then I forgot to include it in my post yesterday). But I don’t think it’s too hard to put into a model (although it’s hard to find the right numbers to use). The model I wrote down in my note is
- 30% chance Bores would oppose an AI pause / strong AI regulations (b/c it’s too “anti-innovation” or something)
- 40% chance Bores would support strong regulations
- 30% chance he would vote for strong regulations but not advocate for them
- 90% chance Bores would support weak/moderate AI regulations
My guess is that ²⁄₃ of the EV comes from strong regulations and ¹⁄₃ from weak regulations (which I just came up with a justification for earlier today but it’s too complicated to fit in this comment), so these considerations reduce the EV to 37% (i.e., roughly divide EV by 3).

FWIW I wouldn’t say “trustworthiness” is the most important thing, more like “can be trusted to take AI risk seriously”, and my model is more about the latter. (A trustworthy politician who is honest about the fact that they don’t care about AI safety will not be getting any donations from me.)

MichaelDickens 14 Nov 2025 16:15 UTC
17 points
10
in reply to: Mo Putera’s comment on: Mo Putera’s Shortform
An important part of my model of college admissions—which unfortunately I didn’t acquire until after I was done applying for colleges—is to consider what type of person becomes a college admissions officer. What percentage of admissions officers majored in math? (Is it possibly as high as 1%? I doubt it.) What percentage of admissions officers understand the significance of something like “solved the Mizohata-Takeuchi conjecture”? What percentage have a vague (or even explicit) disdain for anything math-flavored?

On my model, it is not surprising that admissions officers would fail to appreciate a math prodigy.

Administrators overriding an acceptance does seem like a remarkable failure. I can’t say I’m surprised, but it’s a much worse indictment of those universities, I think.