Vanessa Kosoy(Vanessa Kosoy)

• Vanessa Kosoy 25 Jul 2024 12:38 UTC

  2 points

  0

  in reply to: mesaoptimizer’s comment on: Prize and fast track to al­ign­ment re­search at ALTER

  There was exactly one submission, which was judged insufficient to merit the prize.

• Vanessa Kosoy 15 Jul 2024 6:58 UTC

  2 points

  0

  on: [Er­ror com­mu­ni­cat­ing with LW2 server]

  let $k_{s^{\prime }}:P_j\to R^{U_{\top }}$be a helper function that maps each $a\in V\left(P_i\right)$ to $e_{\top }(s^{\prime },a)$.

  This function is ill-defined outside the vertices.

• Vanessa Kosoy 15 Jul 2024 6:37 UTC

  2 points

  0

  on: [Er­ror com­mu­ni­cat­ing with LW2 server]

  or $s:=(s^{\prime },s^{\prime \prime })\in S_{\wedge }$, we want $P_{\wedge }\left(s\right):=P_{{\sigma }_{\top }\left(s^{\prime }\right)}\left(s^{\prime \prime }\right)$ and $A_{\wedge }\left(s\right):=A_{{\sigma }_{\top }\left(s^{\prime }\right)}\left(s^{\prime \prime }\right)$, so that the actions available are just those of the state in the sub-environment. To achieve this we define ${\sigma }_{\wedge }\left(s\right):={\sigma }_{{\sigma }_{\top }\left(s^{\prime }\right)}\left(s^{\prime \prime }\right)$

  It seems that you’re using Ai and Pi to denote both the action spaces of the top environments and the action space assignment functions of the bottom environments. In addition, there is an implicit assumption that the bottom environments share the same list of action spaces. This is pretty confusing.

• Vanessa Kosoy 15 Jul 2024 6:29 UTC

  2 points

  0

  on: [Er­ror com­mu­ni­cat­ing with LW2 server]

  such that $f_i\left(\right(1-{\gamma }_{\perp }\left)Q_i\right)=A\left(E_i\right)$

  Is A(Ei) supposed to be just Ai?

• Vanessa Kosoy 15 Jul 2024 6:17 UTC

  2 points

  0

  on: [Er­ror com­mu­ni­cat­ing with LW2 server]

  μ×:=μ1×⋯×μk×δ

  Unclear what delta is here. Is it supposed to be p?

• Vanessa Kosoy 15 Jul 2024 6:06 UTC

  2 points

  0

  on: [Er­ror com­mu­ni­cat­ing with LW2 server]

  An atomic environment is constructed by directly providing

  The transition kernel is missing from this list.

• Vanessa Kosoy 15 Jul 2024 6:04 UTC

  2 points

  0

  on: [Er­ror com­mu­ni­cat­ing with LW2 server]

  • a vector space $W$ and linear maps $g:R^U\to W$ and $R^Q:W\to R$ such that for any $q\in Q$, $R^Q\left(q\right)={max}_{\nu \in M\text{s.t.}g\left(\nu \right)=q}{R}^{\nu }\left(\nu \right)$.

  • a H-polytope $Q:=g\left(M\right)\subseteq W$ that we call the occupancy polytope

  Confusing: you’re using Q before you defined it. Also, instead of writing “s.t.” in the subscript, you can write “:”

• Vanessa Kosoy 15 Jul 2024 5:56 UTC

  2 points

  0

  on: [Er­ror com­mu­ni­cat­ing with LW2 server]

  Let’s view each accessible action space $A\left(s\right)$ as the set of randomized policies over $V\left(A\right(s\left)\right)$.

  Seems worth to clarify that this representation is non-unique: multiple distribution over V(A) can correspond to the same point in A.

• Vanessa Kosoy 15 Jul 2024 5:50 UTC

  2 points

  0

  on: [Er­ror com­mu­ni­cat­ing with LW2 server]

  where each $A_i$ and $P_i$ is an HV-polytope

  Too restrictive. P can be an H-polytope, doesn’t need to be an HV-polytope.

• Vanessa Kosoy 15 Jul 2024 5:35 UTC

  2 points

  0

  on: [Er­ror com­mu­ni­cat­ing with LW2 server]

  efficiently^[1]

  The footnote is missing

• Vanessa Kosoy 10 Jul 2024 8:53 UTC

  3 points

  0

  on: Me, My­self, and AI: the Si­tu­a­tional Aware­ness Dataset (SAD) for LLMs

  Can you explain exactly how the score for “anti imitation output control” is defined? You sample the model some number of times, and then compare the resulting frequency to the target probability? How do you translate it to a 0-1 scale?

• Vanessa Kosoy 25 Jun 2024 4:59 UTC

  8 points

  1

  on: I’m a bit skep­ti­cal of AlphaFold 3

  This sounds like valid criticism, but also, isn’t the task of understanding which proteins/​ligands are similar enough to each other to bind in the same way non-trivial in itself? If so, exploiting such similarities would require the model to do something substantially more sophisticated than just memorizing?

• Vanessa Kosoy 9 Jun 2024 14:25 UTC

  LW: 6 AF: 4

  0

  AF

  in reply to: Vanessa Kosoy’s comment on: Vanessa Kosoy’s Shortform

  Here is a modification of the IBP framework which removes the monotonicity principle, and seems to be more natural in other ways as well.

  First, let our notion of “hypothesis” be $\Theta \in {\square }^c(\Gamma \times 2^{\Gamma })$. The previous framework can be interpreted in terms of hypotheses of this form satisfying the condition

  $${pr}_{\Gamma \times 2^{\Gamma }}Br\left(\Theta \right)=\Theta$$

  (See Proposition 2.8 in the original article.) In the new framework, we replace it by the weaker condition

  $$Br\left(\Theta \right)\supseteq ({id}_{\Gamma }\times {diag}_{2^{\Gamma }}{)}_{\ast }\Theta$$

  This can be roughly interpreted as requiring that (i) whenever the output of a program P determines whether some other program Q will run, program P has to run as well (ii) whenever programs P and Q are logically equivalent, program P runs iff program Q runs.

  The new condition seems to be well-justified, and is also invariant under (i) mixing hypotheses (ii) taking joins/​meets of hypotheses. The latter was not the case for the old condition. Moreover, it doesn’t imply that $\Theta$ is downward closed, and hence there is no longer a monotonicity principle^[1].

  The next question is, how do we construct hypotheses satisfying this condition? In the old framework, we could construct hypotheses of the form $\Xi \in {\square }^c(\Gamma \times \Phi )$ and then apply the bridge transform. In particular, this allows a relatively straightforward translation of physics theories into IBP language (for example our treatment of quantum theory). Luckily, there is an analogous construction in the new framework as well.

  First notice that our new condition on $\Theta$ can be reformulated as requiring that

  • $supp\Theta \subseteq {el}^{\Gamma }$

  • For any $s:\Gamma \to \Gamma$ define ${\tau }_s:{\Delta }^c{el}^{\Gamma }\to {\Delta }^c{el}^{\Gamma }$ by ${\tau }_s\theta :={\chi }_{{el}^{\Gamma }}(s\times {id}_{2^{\Gamma }}{)}_{\ast }$. Then, we require ${\tau }_s\Theta \subseteq \Theta$.

  For any $\Phi$, we also define ${\tau }_s^{\Phi }:{\Delta }^c({el}^{\Gamma }\times \Phi )\to {\Delta }^c({el}^{\Gamma }\times \Phi )$ by

  $${\tau }_s^{\Phi }\theta :={\chi }_{{el}^{\Gamma }\times \Phi }(s\times {id}_{2^{\Gamma }\times \Phi }{)}_{\ast }$$

  Now, for any $\Xi \in {\square }^c(\Gamma \times \Phi )$, we define the “conservative bridge transform^[2]” $CBr\left(\Xi \right)\in {\square }^c(\Gamma \times 2^{\Gamma }\times \Phi )$ as the closure of all ${\tau }_s^{\Phi }\theta$ where $\theta$ is a maximal element of $Br\left(\Xi \right).$ It is then possible to see that $\Theta \in {\square }^c(\Gamma \times 2^{\Gamma })$ is a valid hypothesis if and only if it is of the form ${pr}_{\Gamma \times 2^{\Gamma }}CBr\left(\Xi \right)$ for some $\Phi$ and $\Xi \in {\square }^c(\Gamma \times \Phi )$.

  1. ^

     I still think the monotonicity principle is saying something about the learning theory of IBP which is still true in the new framework. Namely, it is possible to learn that a program is running but not possible to (confidently) learn that a program is not running, and this limits the sort of frequentist guarantees we can expect.

  2. ^

     Intuitively, it can be interpreted as a version of the bridge transform where we postulate that a program doesn’t run unless $\Xi$ contains a reason while it must run.

• Vanessa Kosoy 5 Jun 2024 18:06 UTC

  14 points

  0

  in reply to: jacobjacob’s comment on: An­nounc­ing ILIAD — The­o­ret­i­cal AI Align­ment Conference

  International League of Intelligent Agent Deconfusion

• Vanessa Kosoy 16 May 2024 9:19 UTC

  LW: 4 AF: 3

  0

  AF

  in reply to: davidad’s comment on: Lin­ear in­fra-Bayesian Bandits

  Sorry, that footnote is just flat wrong, the order actually doesn’t matter here. Good catch!

  There is a related thing which might work, namely taking the downwards closure of the affine subspace w.r.t. some cone which is somewhat larger than the cone of measures. For example, if your underlying space has a metric, you might consider the cone of signed measures which have non-negative integral with all positive functions whose logarithm is 1-Lipschitz.

• Vanessa Kosoy 11 May 2024 11:00 UTC

  18 points

  12

  in reply to: mesaoptimizer’s comment on: Lin­ear in­fra-Bayesian Bandits

  My thesis is the same research I intended to do anyway, so the thesis itself is not a waste of time at least.

  The main reason I decided to do grad school, is that I want to attract more researchers to work on the learning-theoretic agenda, and I don’t want my candidate pool to be limited to the LW/​EA-sphere. Most qualified candidates would be people on an academic career track. These people care about prestige, and many of them would be reluctant to e.g. work in an unknown research institute headed by an unknown person without even a PhD. If I secure an actual faculty position, I will also be able to direct grad students to do LTA research.

  Other benefits include:

  • Opportunity for networking inside the academia (also useful for bringing in collaborators).

  • Safety net against EA-adjacent funding for agent foundations collapsing some time in the future.

  • Maybe getting some advice on better navigating the peer review system (important for building prestige in order to attract collaborators, and just increasing exposure to my research in general).

  So far it’s not obvious whether it’s going to pay off, but I already paid the vast majority of the cost anyway (i.e. the time I wouldn’t have to spend if I just continued as independent).

• Vanessa Kosoy 11 May 2024 8:59 UTC

  7 points

  0

  in reply to: Selfmaker662’s comment on: Self­maker662′s Shortform

  Creating a new dating app is hard because of network effects: for a dating app to easily attract users, it needs to already have many users. Convincing users to pay for the app is even harder. And, if you expect your app to be only marginally profitable even if it succeeds, you will have a hard time attracting investors.

• Vanessa Kosoy 10 May 2024 8:52 UTC

  5 points

  0

  in reply to: Curt Tigges’s comment on: Dat­ing Roundup #3: Third Time’s the Charm

  FWIW, from glancing at your LinkedIn profile, you seem very dateable :)

Lin­ear in­fra-Bayesian Bandits

• Vanessa Kosoy 9 May 2024 10:25 UTC

  10 points

  10

  on: Dat­ing Roundup #3: Third Time’s the Charm

  One feature of polyamory is that it means continuous auditions of potential replacements by all parties. You are not trading up in the sense that you can have multiple partners, but one thing leads to another and there are only so many hours in the day.

  Polyamory is not that different from monogamy in this respect. It’s just that in monogamy “having a relationship” is a binary: either you have it or you don’t have it. In polyamory, there is a scale, starting from “meeting once in a blue moon” all the way to “living together with kids and joint finances”. So, if in monogamy your attitude might be “I will not trade up unless I meet someone x% better”, then in polyamory your attitude might be “I will devote you y% of my time and will not reduce this number unless there’s someone x% better competing for this slot”. (And in both cases x might be very high.)

  More generally, I feel that a lot of arguments against polyamory fail the “replace with platonic friendship” test. Like, monogamous people also have to somehow balance the time they invest in their relationship vs. friends vs. family vs. hobbies etc, and also have to balance the time allocated to different friends. I know that some mono people feel that sex is some kind of magic pixie dust which makes a relationship completely different and not comparable in any way to platonic friendship, but… Not everyone feels this way? (In both directions: I simultaneously consider romantic relationship comparable to “mere” platonic friendships and also consider platonic friendships substantially more important/​committing than seems to be the culturally-prescribed attitude.)

  Also, it feels like this discussion has a missing mood and/​or a typical mind fallacy. For me, monogamy was a miserable experience. Even aside from the fact you only get to have one relationship, there’s all the weird rules about which things are “inappropriate” (see survey in the OP) and also the need to pretend that you’re not attracted to other people (Not All Mono, but I think many relationships are like that). All the “pragmatic” arguments about why polyamory is bad sound to me similar to hypothetical arguments that gay relationships are bad. I mean, there might be some aspects of gay relationships that are often worse than corresponding aspects of straight relationships. But if you’re gay, a gay relationship is still way better for you! Even if you’re bi and in some sense “have a choice”, it still seems inappropriate to try convincing you about how hetero is much better.

  Warning: About to get a little ranty/​emotional, sorry about that but was hard to express otherwise.

  Finally, not to be that girl, but it’s a little insensitive to talk about this without the least acknowledgement that polyamory is widely stigmatized and discriminated against. I know it’s LessWrong here, we’re supposed to use decoupling norms and not contextualizing norms, and I’m usually fully in favor of that, but it still seems to me that this post would better on the margin, if it had a little in the way of acknowledging this asymmetry in the debate.

  Instead, the OP talks about “encouraging widespread adaptation”. What?? I honestly don’t know, maybe in the Mythic Bay Area, someone is encouraging widespread conversion to polyamory. In the rest of the world, we only want (i) not be stigmatized (ii) not be discriminated against (iii) having some minimal awareness that polyamory is even an option (it was certainly an eye-opening discovery for me!) and (iv) otherwise, being left alone, and not have mono people endlessly explain to us how their way is so much better [My spouse tells me this last bit was too combative. Sorry about that: we are certainly allowed to have respectful discussion about the comparative advantages of different lifestyles.]