Alexander Gietelink Oldenziel

Featured in:

Articles

Permanents: much more than you wanted to know — LessWrong

Jan 16, 2025 | lesswrong.com | Dmitry Vaintrob |Alexander Gietelink Oldenziel

Today's "nanowrimo" post is a fun longform introduction to permanents and their properties, organized in the way I wish it had been explained to me. Note before going on: this is not my field, and this post is even more likely than usual to contain incorrect statements or bugs. Recall that given an n×n matrix A with coefficients Aij, its determinant is a sum over permutations σ on n letters with j=σ(i), det(A)=∑σ(−1)σ∏iAiσ(i). Here the notation (−1)σ denotes the parity of a permutation.
There aren't enough smart people in biology doing something boring — LessWrong

Oct 21, 2024 | lesswrong.com | Abhishaike Mahajan |Alexander Gietelink Oldenziel

Note: this essay is co-written with Eryney Marrogi, who helped seed the initial idea and edited this piece a fair bit. On a related note, I’m helping him run an NYC meetup event on Wednesday, November 20th in Williamsburg, you should sign up here to come! If you like biology, ML, or human connection, I highly recommend attending!🦉There aren't enough smart people in biology doing something boring. At least in industry.
Timaeus is hiring! — LessWrong

Jul 12, 2024 | lesswrong.com | Jesse Hoogland |Stan van Wingerden |Alexander Gietelink Oldenziel |Daniel Murfet

TLDR: We’re hiring two research assistants to work on advancing developmental interpretability and other applications of singular learning theory to alignment. About UsTimaeus’s mission is to empower humanity by making breakthrough scientific progress on alignment.
Announcing ILIAD — Theoretical AI Alignment Conference — LessWrong

Jun 5, 2024 | lesswrong.com | Alexander Gietelink Oldenziel

We are pleased to announce ILIAD — a 5-day conference bringing together 100+ researchers to build strong scientific foundations for AI alignment. ***Apply to attend by June 30!***When: Aug 28 - Sep 3, 2024Where: @Lighthaven (Berkeley, US)What: A mix of topic-specific tracks, and unconference style programming, 100+ attendees. Topics will include Singular Learning Theory, Agent Foundations, Causal Incentives, Computational Mechanics and more to be announced.
Are very low P(Doom) estimates epistemically justifiable? — LessWrong

Mar 19, 2024 | lesswrong.com | Nathan Barnard |Alexander Gietelink Oldenziel

Possible Topics Both checked! Extreme percentages for P(Doom) are not epistemically justified Scheduling PreferencesSyncAsyncNotes NathanBarnard Okay Okay Alexander Gietelink Oldenziel Okay Okay Next steps Chat about topic and potential scheduling (tip: when2meet.com is a great scheduling tool) If you agree on something, have your dialogue Edit (remove any side chats like this message, and feel free to request editing services from the LessWrong team, button below) Publish! Can you post the...
0th Person and 1st Person Logic — LessWrong

Mar 10, 2024 | lesswrong.com | Adele Lopez |Alexander Gietelink Oldenziel |Nate Showell

Truth values in classical logic have more than one interpretation. In 0th Person Logic, the truth values are interpreted as True and False. In 1st Person Logic, the truth values are interpreted as Here and Absent relative to the current reasoner. Importantly, these are both useful modes of reasoning that can coexist in a logical embedded agent.
Semi-Simplicial Types, Part I: Motivation and History — LessWrong

Mar 9, 2024 | lesswrong.com | Alexander Gietelink Oldenziel

Synthetics comes to LessWrong! Very cool. For people just tuning in wondering what the significance of this math is: I see this kind of research potentially may lead to new and powerful methods to deal with self-reflection & self-modification. At the moment, current tools are quite limited. I'd be curious what your take on Benabou's perspective is which sees fibrations as more fundamental than indexed categories and would probably bristle at trying to prove they're 'equal'/ equivalent.
Timaeus's First Four Months — LessWrong

Feb 28, 2024 | lesswrong.com | Jesse Hoogland |Daniel Murfet |Stan van Wingerden |Alexander Gietelink Oldenziel

Timaeus was announced in late October 2023, with the mission of making fundamental breakthroughs in technical AI alignment using deep ideas from mathematics and the sciences. This is our first progress update.
Will quantum randomness affect the 2028 election? — LessWrong

Jan 24, 2024 | lesswrong.com | Steven Byrnes |Thomas Kwa |Gerald M. Monroe |Alexander Gietelink Oldenziel

Ok, so in the box of gas case, you have individual gas molecules following newtonian physics with no process to give any kind of structure at all. However, a human brain of a voter is more like an optimizing process.
1a3orn's Shortform — LessWrong

Jan 5, 2024 | lesswrong.com | Alexander Gietelink Oldenziel

Just a few quick notes / predictions, written quickly and without that much thought:(1) I'm really confused why people think that deceptive scheming -- i.e., a LLM lying in order to post-deployment gain power -- is remotely likely on current LLM training schemes. I think there's basically no reason to expect this.