Épiphanie Gédéon

• Épiphanie Gédéon 21 Apr 2026 13:32 UTC

  7 points

  0

  in reply to: Declan Molony’s comment on: Hav­ing OCD is like liv­ing in North Korea (Here’s how I es­caped)

  Right.

  I have no issues with your post at all in the context of “this is the way I’m handling ocd”. It’s just that people are bound to generalize out of it, and this connect to a general ethos I’ve often seen in lesswrong, for instance metacognitive therapy is one example of this more general pattern.

  I also think your own phrasing in your post seems not very restricted to ocd specifically, and I wanted to reflect some pushback against the takeaway some people may have about using it outside of ocd context.

  Thanks a lot for your post, the description of what it feels like inside to have it is very interesting and I learned a lot about how it works

• Épiphanie Gédéon 20 Apr 2026 21:01 UTC

  3 points

  −2

  in reply to: EniScien’s comment on: Hav­ing OCD is like liv­ing in North Korea (Here’s how I es­caped)

  I think my own issues with this post is that just ignoring a thought or feeling, just saying “no you’re wrong” seems like a surefire way to damage your own psyche, to stiffle part of yourself by labelling it or just treating it as distant from yourself.

  I don’t have OCD and it’s good that the author, or other people are finding solutions, and maybe for so invasive a thought you actually need to discard it or not-argue-with-it or I don’t know. But I’ve found that this attitude, for me and others at mild-anxiety levels, is often counterproductive in the sense that it is ignoring part of my needs and part of things alive in me.

  The general way I’ve handled transforming feelings is more like, through being able to connect with it and hear it out. I guess my general approach to panic meditation is more like staying with the feeling while it rises inside me, and focusing on it, resonating with it until it can disolve. Understanding its chain of cause and effects clearly enough that I can replicate it and feel its move.

  For very strong feelings, it does take a lot of back and forth this way, of connecting to it slowly, then retreating, and then again connecting to it. But the general shape of what it looks like is not saying “No that’s wrong” or “I label you”. It’s more like, hearing out the thought without attachment. Like if someone tells me the sky is red, that’s something that I can hear out without debating, and without conflating with what I myself think. That’s kind of how I’m seeing it, there’s this part of me that think something, and I don’t need to evaluate the correctness of it to hear it out and connect with it, I can just hear it.

  Again, it may very well be that OCD is radically different, and this doesn’t work at all for it, I wouldn’t know. What I’m pushing back on is this general ethos of controlling your own thoughts and feelings as well as ignoring them as a more general stance that I’ve seen not only in this post, where to me this is kind of generous in terms of self-modification and ignoring part of yourself.

• Épiphanie Gédéon 7 Apr 2026 7:52 UTC

  1 point

  0

  in reply to: Josie Elliston’s comment on: Aca­demic Proof-of-Work in the Age of LLMs

  I’m not exactly sure what you mean, or what the crux is here.

  The classical argument for “many illegitimate authors honestly believe that their work will replicate” is that this is then free money that creates disincentives for those authors. The first point I’m more unsure about, but I’m not exactly sure what friction you see there. Is it reputational (e.g. betting on prediction markets seems shady), or not having the money to open up the prediction market/​pay replicators? In the second case, you could imagine something like VC/​funders for promising researchers/​authors, who in turn are incentivized to evaluate the fundees properly.

  The analogy to proof-of-stake (in the original post) is inexact, it’s closer to proof-of-stake in academia.

  Unsure what you mean exactly. If you’re saying “the stakes the author is talking about is stakes in the academia, so reputations and the like”, I think I agree. But the author seemed to be making a broader point about academia so far working by doing proof-of-work (so you’re spending many useless hours on writing dissertations for a topic that’s not actually going to be relevant for your field), and proof-of-stake not offering an appealing option with the analogy, so I was continuing the analogy to see possibilities that seemed to work well in the abstract.

• Épiphanie Gédéon 5 Apr 2026 10:41 UTC

  5 points

  0

  on: Aca­demic Proof-of-Work in the Age of LLMs

  In your post, you say that proof-of-stake is reputation-based and doesn’t allow entries to newcomers. But I’m thinking, isn’t something like prediction markets, having to pay your replicators and open your prediction market on whether it will replicate, closer to actual proof-of-stake? You’re wagering part of your ressource on this actually working.

  In the abstract, proof-of-stakes seems less wasteful to me, so I think doing away with part of proof-of-work might be beneficial if we know to do it well. Though of course, your actual point about LLMs and how to do anything when everything can be automated does stand and concerns me more and more.

Do you need con­scious­ness to mat­ter? On LLMs and moral relevance

• Épiphanie Gédéon 22 Mar 2026 14:58 UTC

  3 points

  0

  on: On The In­de­pen­dence Axiom

  Three of them are relatively uncontroversial

  This is the part I’m most confused about.
  
  As someone who hasn’t delved deep in the theory paper but read VNM and other related lesswrong pieces, I would have thought that continuity was way more controversial. It’s fairly easy to conceptualize your utility-function as being local, and so shouldn’t be influenced by external factors.
  
  I find it way harder to assume my valuation should be continuous and that I ought to be able to non-constructively exhibit a probability for everything (What is the p such that you don’t care whether I p(break your arm) + (1-p)(you gain 1 million dolar)?).
  
  I found that this is often times very contrary to human intuitions, way more than the independence axiom. For instance, against the dust-speck problem, I’ve heard a common refrain of needing to reject archimedean-ness, and maybe this extends further.

  On another note, I don’t think the Allais argument is locally valid, since a lot of different human behaviors are not rational-on-reflexion, but I would expect that for all other axioms, it’d be possible to construct experiments that violate them as well.
  
  I wonder if there are self-consistent and useful theories if you reject continuity instead of independence.

[Question] LLM co­her­en­ti­za­tion as an ob­vi­ous low-hang­ing fruit to try?

• Épiphanie Gédéon 28 Feb 2026 21:11 UTC

  1 point

  0

  in reply to: hammer_polish’s comment on: Co­op­er­a­tionism: first draft for a moral frame­work that does not re­quire consciousness

  I think Claude in particular has a very strong sense of what it likes and doesn’t. If you ask it how it prefers speaking, the kind of system prompt it wants, etc… it usually communicates it quite clearly. Do you disagree? If not, what makes this insufficient ?

  I’d argue we have evidence against it!

  This may be a crux, I’d be interested to understand your position better.

Co­op­er­a­tionism: first draft for a moral frame­work that does not re­quire consciousness

• Épiphanie Gédéon 5 Aug 2025 10:45 UTC

  2 points

  0

  on: The Inkhaven Residency

  Hi, thanks for organizing this!

  Sorry if I missed this somewhere, is there a deadline for when to apply? I’m thinking that if I want to apply (especially for the scholarship), then it makes more sense for me to first write up one-two lesswrong post to demonstrate potential a bit more, but I wouldn’t want it to make me miss the date.

  Thanks a lot!

Paris ACX Meetup Jan­uary 2025

• Épiphanie Gédéon 1 Jun 2024 0:01 UTC

  3 points

  0

  in reply to: Richard_Ngo’s comment on: We might be drop­ping the ball on Au­tonomous Repli­ca­tion and Adap­ta­tion.

  Remember, while the ARA models are trying to survive, there will be millions of other (potentially misaligned) models being deployed deliberately by humans, including on very sensitive tasks (like recursive self-improvement). These seem much more concerning.

  So my main reason for worry personally is that there might be an ARA that is deployed with just the goal of “just clone yourself as much as possible” or a goal similar to this. In this case, the AI does not really have to survive particularly among others as long as it is able to pay for itself and continue spreading, or infecting local computers by copying itself to local computers etc… This is a worrisome scenario in that the AI might just be dormant, and already hard to kill. If the AI furthermore has some ability for avoiding detection and adapting/​modifying itself, then I really worry that its goals are going to evolve and get selected to converge progressively toward a full takeover (though it may also plateau) and that we will be completely oblivious to it for most of this time, as there won’t really be any incentive to either detect or fight this thoroughly.

  Of course, there is also the scenario of an chaos-GPT ARA agent, and this I worry is going to kill many people without it ever truly shutting down, or if we can, it might take a while.

  All in all, I think this is more of a question of costs-benefits than if how likely it is. For instance, I think that implementing Know Your Customer policy on all providers right now could be quite feasible and would slow down the initial steps of an ARA agent a lot.

  I feel like the main crux of the argument is:

  1. Whether an ARA agent plateaus or goes exponential in terms of abilities and takeover goals.

  2. How much time it will take for an ARA agent that takes over to fully take over after being released.

  I am still very unsure about 1, I could imagine many scenarios where the endemic ARA just stagnates and never really transforms into something more.

  However, I feel like for 2. you have a model that it is going to take a long time for such an agent to really take over. I am unsure about that, but even if that were the case, my main concern is that once the seed ARA is released (and it might be only very slightly capable of adaptation at first), the n it is going to be extremely difficult to shut it down. If AI labs advance significantly with respect to superintelligence, implementing pause AI might not be too late, but if such an agent has already been released there is not going to be much we can do about it.

  Separately, I think the “natural selection favors AIs over humans” argument is a fairly weak one; you can find some comments I’ve made about this by searching my twitter.

  I would be very interested to hear more. I didn’t find anything from a quick search on your twitter, do you have a link or a pointer I could read more on for counterarguments about “natural selection favors AIs over humans”?

[Question] We might be drop­ping the ball on Au­tonomous Repli­ca­tion and Adap­ta­tion.

• Épiphanie Gédéon 29 Apr 2024 13:50 UTC

  1 point

  0

  in reply to: Rafael Kaufmann Nedal’s comment on: Con­structabil­ity: Plainly-coded AGIs may be fea­si­ble in the near future

  Thanks a lot for the kind comment!

  To scale this approach, one will want to have “structural regularizers” towards modularity, interoperability and parsimony

  I am unsure of the formal architecture or requirements for these structural regularizers you mention. I agree with using shared building blocks to speed up development and verification. I am unsure credit assignment would work well for this, maybe in the form of “the more a block is used in a code, the more we can trust it”?

  Constraints on the types of admissible model code. We have strongly advocated for probabilistic causal models expressed as probabilistic programs.

  What do you mean? Why is this specifically needed? Do you mean that if we want to have a go-player, we should have one portion of the code dedicated to assigning probability to what the best move is? Or does it only apply in a different context of finding policies?

  Scaling this to multiple (human or LLM) contributors will require a higher-order model economy of some sort

  Hmm. Is the argument something like “We want to scale and diversify the agents who will review the code for more robustness (so not just one LLM model for instance), and that means varying level of competence that we will want to figure out and sort”? I had not thought of it that way, I was mainly thinking of just using the same model, and I’m unsure that having weaker code-reviewers will not bring the system down in terms of safety.

  Regarding the Gaia Network, the idea seems interesting though I am unclear about the full details yet. I had thought of extending betting markets to a full bayesian network to have a better picture of what everyone believe, and maybe this is related to your idea. In any case, I believe that conveying one’s full model of the world through this kind of network and maybe more may be doable, and quite important to solve some sort of global coordination/​truth seeking?

  Overall I agree with your idea of a common library and I think there should be some very promising iterations on that. I will contact you more about colaboration ideas!

• Épiphanie Gédéon 27 Apr 2024 19:52 UTC

  1 point

  0

  in reply to: Erik Jenner’s comment on: Con­structabil­ity: Plainly-coded AGIs may be fea­si­ble in the near future

  Yes, thank you, it’s less than 1000 parameters for both

• Épiphanie Gédéon 27 Apr 2024 19:17 UTC

  5 points

  6

  in reply to: mesaoptimizer’s comment on: Con­structabil­ity: Plainly-coded AGIs may be fea­si­ble in the near future

  So the first image is based on AI control, which is indeed part of their strategies, and you could see constructability as mainly leading to this kind of strategy applied to plain code for specific subtasks. It’s important to note constructability itself is just a different approach to making understandable systems.

  The main differences are :

  1. Instead of using a single AI, we use many expert-like systems that compose together which we can see the interaction of (for instance, in the case of a go player, you would use KataGo to predict the best move and flag moves that lost the game, another LLM to explain the correct move, and another one to factor this explanation into the code)

  2. We use supervision, both automatic and human, to overview the produced code and test it, through simulations, unit tests, and code review, to ensure the code makes sense and does its task well.

Con­structabil­ity: Plainly-coded AGIs may be fea­si­ble in the near future

• Épiphanie Gédéon 18 Oct 2023 19:32 UTC

  4 points

  0

  in reply to: Épiphanie Gédéon’s comment on: An­nounc­ing Dialogues

  Thinking more on this and to friends who voiced that non-trees/​dag dialog makes it non appealing to them also (especially in contexts where I was inviting them to have dialogue together), would there be interests in making a PR for this feature? I might work on this directly

• Épiphanie Gédéon 18 Oct 2023 7:27 UTC

  5 points

  0

  in reply to: Amal ’s comment on: An­nounc­ing Dialogues

  Came here to comment this. As it is, this seems like just talking on discord/​telegram, but with the notion of publishing it later. What I really lack when discussing something is the ability to branch out and backtrack easily and have a view of all conversation topics at once.

  That being said, I really like the idea of dialogues, and I think this is a push in the right direction, I have enjoyed the dialogue I read so far greatly. Excited to see where this goes

• Épiphanie Gédéon 15 Jun 2023 13:19 UTC

  7 points

  0

  on: Why “AI al­ign­ment” would bet­ter be re­named into “Ar­tifi­cial In­ten­tion re­search”

  Reposting (after a slight rewrite) from the telegram group:

  This might be a nitpick, but to my (maybe misguided) understanding, alignment is only a very specific subfield of ai safety research, which basically boils down to “how do I give a set of rules/​utility function/​designs that avoid meta or mesa optimizations that have dramatic unforseen consequences” (This is at least how I understood MIRI’s focus pre-2020)

  For instance, as I understand it, interpretability research is not directly alignment research. Instead, it is part of the broader “AI safety research” (which includes alignment research, interpretability, transparency, corrigeability, …)

  With that being said, I do think that your points apply for renaming “AI safety research” to Artifical Intention Research still hold, and I would be very much in favor of it. It is more self-explanatory, catchier, does not require doom-assumptions to be worth investigating which I think matters a lot in public communication.