Alexander Gietelink Oldenziel

Karma: 5,984

″ (...) the term technical is a red flag for me, as it is many times used not for the routine business of implementing ideas but for the parts, ideas and all, which are just hard to understand and many times contain the main novelties.”
- Saharon Shelah
”A little learning is a dangerous thing ;
Drink deep, or taste not the Pierian spring” - Alexander Pope

As a true-born Dutchman I endorse Crocker’s rules.

For my most of my writing see my short-forms (new shortform, old shortform)

Twitter: @FellowHominid

Personal website: https://sites.google.com/view/afdago/home

Alexander Gietelink Oldenziel 24 Sep 2025 12:44 UTC
30 points
5
on: Alexander Gietelink Oldenziel’s Shortform
Reward is not the optimization target.
The optimization target is the Helmholtz free energy functional in the conductance-corrected Wasserstein metric for the step-size effective loss potential in the critical batch size regime for the weight-initialization distribution as prior up to solenoidal flux corrections

Alexander Gietelink Oldenziel 24 Sep 2025 12:30 UTC
3 points
0
in reply to: neo’s comment on: Global Call for AI Red Lines—Signed by Nobel Laureates, Former Heads of State, and 200+ Prominent Figures
I suppose the problem is that in most fast takeoff scenarios there is little direct evidence before it happens and one should reason on priors.

Alexander Gietelink Oldenziel 17 Sep 2025 12:36 UTC
LW: 6 AF: 5
4
AF
in reply to: Thomas Kwa’s comment on: Daniel Kokotajlo’s Shortform
Drone countermeasures are an idle hope. The only real counter to drones is more drones.
Lasers, shotguns, tank redesign [no holes!], nets, counter-drones, flak etc will all be part of the arsenal surely but thinking drone countermeasures are going to restore the previous generation’s war doctrine is as silly as thinking that metallurgy innovations will reverse the gunpowder age.
The ~~future~~ present of warfare is drones, drones, drones.

Alexander Gietelink Oldenziel 17 Sep 2025 12:30 UTC
LW: 4 AF: 3
2
AF
in reply to: Daniel Kokotajlo’s comment on: Daniel Kokotajlo’s Shortform
It seems nobody outside Ukraine/Russia is actually at the leading edge of where the reality of military technology is. That includes Hamas. Even using the drone doctrine from two years ago would be devastating to the Israelis. Probably they don’t have the resources, organization to do so.
[Even Ukraine itself is not really there—there are clearly many simple ways drones and drone manufacturing could be improved they haven’t had the time and resources to focus on yet. ]
Expect terror/resistance groups to start utilizing drones en masse in the next few years.

Alexander Gietelink Oldenziel 17 Sep 2025 12:20 UTC
4 points
7
in reply to: Cleo Nardo’s comment on: Alexander Gietelink Oldenziel’s Shortform
Referring to particular models and particular deployment plans and particular catastrophe doesn’t help—the answer is the same.
We don’t know how to scientifically quantify any of these probabilities.

Alexander Gietelink Oldenziel 16 Sep 2025 21:39 UTC
19 points
7
in reply to: Jacob_Hilton’s comment on: Jacob_Hilton’s Shortform
Couldn’t agree more!
One of the saddest ways we would die is if we fail to actually deploy enough theory/math people to work on prompting AIs to solve alignment in the next two-three years, even if it would be totally possible to solve alignment this way.
P.S. Please get into contact if you are interested in this.

Alexander Gietelink Oldenziel 16 Sep 2025 21:36 UTC
6 points
14
in reply to: Cleo Nardo’s comment on: Alexander Gietelink Oldenziel’s Shortform
I’m having trouble seeing that (2) is actually a thing?
The whole problem is that there is no generally agreed ” chance of catastrophe” so ” same change of catastrophe” has no real meaning.
It seems this kind of talk is being backchained from what governance people want as opposed to the reality of safety guarantees or safety/risk probabilities—which is that they don’t meaningfully exist [outside of super heuristic guesses].
Indeed, to estimate this probability in a non-bullshit way we exactly need fundamental scientific progress, i.e. (1).
EA has done this exercise a dozen times: if you ask experts the probabilities of doom it ranges all the way from 99% to 0.0001 %.
Will that change? Will expert judgement converge? Maybe. Maybe not. I don’t have a crystal ball.
Even if they do [outside of meaningful progress on (1)] those probabilities won’t actually reflect reality as opposed to political reality.
The problem is there is no ′ scientific’ way to estimate p(doom) and as long as we don’t make serious progress on 1. there won’t be.
I don’t see how cot/activation/control monitoring will have any significant and scientifically -grounded [as opposed to purely story-telling/politics] influence in a way that can be measured and can be utilized to make risk-tradeoffs.

Alexander Gietelink Oldenziel 16 Sep 2025 15:34 UTC
6 points
0
in reply to: kaleb’s comment on: Alexander Gietelink Oldenziel’s Shortform
I didn’t intend it that way, though admittedly that is a valid reading. From my own point of view both functions seem significant.

Alexander Gietelink Oldenziel 16 Sep 2025 13:46 UTC
26 points
8
on: Alexander Gietelink Oldenziel’s Shortform
Additive versus Multiplicative model of AI-assisted research
Occasionally one hears somebody say “most of the relevant AI-safety work will be done at crunch time. Most work being done now at present is marginal”.
One cannot shake the suspicion that this statement merely reflects the paucity of ideas & vision of the speaker. Yet it cannot be denied that their reasoning has a certain logic: if, as seems likely, AI will become more and more dominant in AI alignment research than maybe we should be focusing on how to safely extract work from future superintelligent machines rather than hurting our painfully slow mammalian walnuts to crack AI safety research today. I understand this to be a key motivation for several popular agendas AI safety.
Similarly, many Pause advocates argue that pause advocacy is more impactful than direct research. Most will admit that a Pause cannot be maintained indefinitely. The aim of a Pause would be to buy time to figure out alignment. Unless one believes in very long pauses, implicitly it seems there is an assumption that research progress will be faster in the future.
Implicitly, we might say there is underlying ” Additive” model of AI-assisted research: there is a certain amount of research that is to be done to solve alignment. Humans do some of it, AI does some (more). If the sum is large enough we are golden.
Contrast this with a ” multiplicative” model of AI-assisted research:
Humans increasingly resort to a supervisory and directing role for AI alignment research by AIs. Human experts become ‘research managers’ of AI grad students. The key bottleneck increasingly is the capacity for humans to effectively oversee, supervise, direct, and judge the AI’s research output. In this model research effort by humans and AI is multiplicative. The better the understanding of the humans, the more AI can be effectively leveraged.
These are highly simplified models of course. I still think it’s worthwhile to keep them in mind since they imply very different courses of action. In the additive framework direct research is somewhat marginal. In the multiplicative model every research XP point that humans build today is worth 10x tomorrow in effective research output at crunch time. ^[1]
1. ^
  Moreover, in the latter model it is especially important to start thinking today about very ambitious plans/ideas/methods that are less likely to be obsoleted the moment the next generation of AI comes along.

Alexander Gietelink Oldenziel 15 Sep 2025 13:46 UTC
2 points
0
in reply to: mako yass’s comment on: MakoYass’s Shortform
I wonder what the evidence is that politicians trading on legislative decisions is very harmful.
It seems distasteful to be sure. A moral failure. But how bad is it really?

Alexander Gietelink Oldenziel 15 Sep 2025 13:44 UTC
11 points
11
in reply to: Adam Zerner’s comment on: adamzerner’s Shortform
>> Anecdotally I feel like there are a fair amount of examples of people who have kids and end up regretting it, at least to a meaningful degree.

The social desirability bias against saying one regrets having kids is very intense. So although I would very much not say that the following observation is anything but a highly biased sample: I personally have never met a person regretting having children in real life. I’ve heard parents complain for sure—true regrets seem to be rare.

Alexander Gietelink Oldenziel 13 Sep 2025 10:32 UTC
28 points
0
in reply to: Thane Ruthenis’s comment on: johnswentworth’s Shortform
… and so at long last John found the answer to alignment
The answer was Love
and it had always has been

Alexander Gietelink Oldenziel 5 Sep 2025 22:15 UTC
2 points
0
in reply to: Wei Dai’s comment on: Anthropic’s leading researchers acted as moderate accelerationists
Does the appriopriate [soft] reference class scale with intersimulizability of agents?
i.e. generally greater more computationally powerful agents are better at simulating other agents and this will generically push towards the regime where FDT gives a larger reference class.
The asymptote would be some sort of acausal society of multiverse higher-order cooperators.

Alexander Gietelink Oldenziel 23 Aug 2025 15:02 UTC
84 points
−1
on: Banning Said Achmiz (and broader thoughts on moderation)
Fwiw I’ve found Said’s comments to be clear, crisp and valuable. I don’t recall being ever annoyed by his comments and found him a most useful bloodhound for bad epistemic practices and rhetorics. Many cases that Said’s comment is the only good, clear, and crisp critic of vagueposting and applauselighting.
The examples in this post don’t seem compelling at all. One of the primary examples seems to be Duncan who comes off [from a distance] as thin-skinned and obscurantist, emotionally blowing up at very fair criticism.
Despite my disagreement I endorse Habryka unilaterally taking these kinds of decisions and approve of his transparency and conduct in this matter.
Farewell, lesswrong gadfly. You will be missed.
What links here?

Alexander Gietelink Oldenziel 19 Aug 2025 18:11 UTC
4 points
−4
in reply to: Leon Lang’s comment on: Leon Lang’s Shortform
Agreed. The primary thing Solomonoff induction doesn’t take into account is computational complexity/ compute. But… you can simply include a reasonable time-penalty and most of the results mostly go through. It becomes a bit more like logical inductors.
Solomonoff induction also dovetails (hah) nicely with the fact that next-token prediction was all you need for intelligence.^[1]
1. ^
  well almost, the gap is exactly AIXI

Alexander Gietelink Oldenziel 8 Aug 2025 10:41 UTC
−4 points
0
in reply to: sunwillrise’s comment on: Inscrutability was always inevitable, right?
MIRI lost the Mandate of Heaven smh

Alexander Gietelink Oldenziel 7 Aug 2025 9:08 UTC
2 points
0
in reply to: Thomas Kwa’s comment on: Alexander Gietelink Oldenziel’s Shortform
Oh wild. It’s clearly propaganda. But also incredibly valuable information. itsThe West would so well to listen carefully to what adversaries are saying. They are certainly listening carefully to us!
Thanks for the alert Thomas. Subscribed.

Alexander Gietelink Oldenziel 29 Jul 2025 11:34 UTC
4 points
0
in reply to: Alex_Altair’s comment on: Alex_Altair’s Shortform
1. Gemini: https://docs.google.com/document/d/1m6A5Rkf0NzPsCMt8c1Qb-o9pTWup-zk5epQNYX_cdo4/edit?usp=sharing
  
  2. Chatgpt: https://chatgpt.com/share/6888b1b6-0e88-8011-8b41-d675d3aefb04
  
  seems to me that there is a lot of good content here already.

Alexander Gietelink Oldenziel 28 Jul 2025 13:17 UTC
5 points
2
in reply to: Alex_Altair’s comment on: Alex_Altair’s Shortform
What does Gemini say? Seems like a perfect set of questions to ask a modern LLM.

Alexander Gietelink Oldenziel 22 Jul 2025 18:36 UTC
7 points
0
in reply to: williawa’s comment on: williawa’s Shortform
@Dmitry Vaintrob