Here is a little Q&A Can you explain your position quickly? I think autonomous replication and adaptation in the wild is under-discussed as an AI threat model. And this makes me sad because this is one of the main reasons I'm worried. I think one of AI Safety people's main...
Charbel-Raphaël Segerie and Épiphanie Gédéon contributed equally to this post. Many thanks to Davidad, Gabriel Alfour, Jérémy Andréoletti, Lucie Philippon, Vladimir Ivanov, Alexandre Variengien, Angélina Gentaz, Simon Cosson, Léo Dana and Diego Dorn for useful feedback. TLDR: We present a new method for a safer-by design AI development. We think...
Slime Mold Time Mold (SMTM) has just published the results of their studies on the potato diet. The idea is to eat nothing but potatoes for four weeks, and report how it went. You can read SMTM's reasoning here, the basic idea is that they've observed some annectdotal data point...
Do you enjoy reading Scott Alexander’s blog ACX? Do you enjoy the kind of topics discussed there (rationality, AI, psychiatry, effective altruism, science, etc.)? Do you want to have interesting conversations with people who enjoy that stuff?
If so, come and join us to chat about cool things! We'll have board games, big whiteboards, good food, comfy couches, meditation mats and lots of good vibes!
Please feel free to come even if you feel awkward about it, even if you’re not ‘the typical ACX reader’, even if you’re worried people won’t like you, etc.
Communication about the event will mostly happen on our Discord server.
More details and location available on the Partiful event once you RSVP.
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... (read 389 more words →)
Here is a little Q&A
Can you explain your position quickly?
I think autonomous replication and adaptation in the wild is under-discussed as an AI threat model. And this makes me sad because this is one of the main reasons I'm worried. I think one of AI Safety people's main proposals should first focus on creating a nonproliferation treaty. Without this treaty, I think we are screwed. The more I think about it, the more I think we are approaching a point of no return. It seems to me that open source is a severe threat and that nobody is really on the ball. Before those powerful AIs can self-replicate and adapt, AI development... (read 1195 more words →)
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... (read more)
Yes, thank you, it's less than 1000 parameters for both
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 :
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)
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.
Charbel-Raphaël Segerie and Épiphanie Gédéon contributed equally to this post.
Many thanks to Davidad, Gabriel Alfour, Jérémy Andréoletti, Lucie Philippon, Vladimir Ivanov, Alexandre Variengien, Angélina Gentaz, Simon Cosson, Léo Dana and Diego Dorn for useful feedback.
TLDR: We present a new method for a safer-by design AI development. We think using plainly coded AIs may be feasible in the near future and may be safe. We also present a prototype and research ideas on Manifund.
Epistemic status: Armchair reasoning style. We think the method we are proposing is interesting and could yield very positive outcomes (even though it is still speculative), but we are less sure about which safety policy would use it in the... (read 3684 more words →)
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
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
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.
Hello everyone!
We are organising an ACX spring meetup in Paris, in the Caroussel Garden (near the Louvres and Tuileries, left of the Arch from the Louvres, on the grass near the statues). We'll have an ACX Meetup sign. Plus code: https://plus.codes/8FW4V86J+GH
Hello everyone!
We are organising a monthly SSC meetup in Paris. For privacy reasons, the exact location details are written in an expiring framabin located at the following link with password 'FebruaryMeetups'
As usual :
(
Also, I wouldn’t ban orgies, that won’t work
I'm not sure on that point anymore. Monkeypox' spread seems so slow, and the fact that only men gets infected while the proportions of women who have sex with men having sex with men is not that narrow. I wonder if the spread of Monkeypox is not mostly driven by orgies/big events at the moment, and if it's not the best moment to do this. Though it might be a bit too late now, I think it'd have worked two-four weeks ago)
People can totally understand all of this, and also people mostly do understand most of this
On the other hand, the very fact that we say Monkeypox is spreading within the community of Men having Sex with Men is symbolic of the problem, to me. Being MSM and being in this monkeypox-spreading community is very correlated sure, but not synonymous, the cluster we're talking about is more specific: It's the cluster of people participating in orgies, have sex with other strangers several times a week, etc.
Seeing how we're still conflating the two in discussions I've seen, I can understand the worries that this will reflect on the non-straight community, though I do agree... (read more)
Slime Mold Time Mold (SMTM) has just published the results of their studies on the potato diet. The idea is to eat nothing but potatoes for four weeks, and report how it went.
You can read SMTM's reasoning here, the basic idea is that they've observed some annectdotal data point of some people losing substantive weight while eating nothing but potatoes and want to reproduce the result.
Natália Coelho Mendonça has written in a very detailed and well-written article why it was probably not lithium, SMTM's leading hypothesis of why obesity is so prevalent.
As SMTM's potato diet is not directly linked with lithium, some readers might think that even if SMTM was wrong on... (read 4715 more words →)
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!