Hah, I did the same exact thing and came here to say that :) I was looking at wiring diagrams and telling myself I could wire up some arduino circuits for it but gave up when when I realized I could just press the button!
edit: although mine was an ancient system from the early 90s. It was just replaced with a modern system a couple months ago. At my previous apartment I had wanted to set up a system that would allow either my then partner or I to activate the callbox and have it set for a VOIP number since we could only put one number on the box.
I added a super cheap and bad embedding database in a project that allows the agent to call a tool for searching all the content it's built, it seems to work pretty well! This way the agent doesn't need to call a bunch of list tools (which I was worried would introduce lost of data to the context), and can find things based on fuzzy search.
I realize this comes up every so often, but I was just looking at this the other day :) A related idea is wang tiles, which are a way to construct a tileset such that you can place them without ever running into a contradiction.
Could it be because nuclear is highly centralized? I would expect that something like solar/wind power would be better for decentralization (in a war).
Even if you don't blow up a nuclear plant, it seems like cutting the power from one would be relatively easy.
Russia has refrained from hitting Ukraine's nuclear plants directly, and Ukraine has more or less kept them connected to the grid (albeit with nonstop repair efforts).
Transformer substations are more vulnerable targets but it's hard to be decentralized enough to not have those.
I don't know how far it would get, but I imagine that a FAANG will be able to get the farthest here by virtue of having mountains of corporate data that they have complete ownership over.
They’d probably get the farthest, but they won’t pursue that because they don’t want to end up leaking the original data from training.
It is possible in regular language/text subsets of models to reconstruct massive consecutive parts of the training data [1], so it ought to be possible for their internal code, too.
Copyright for me not for thee? :) That's a good point though. Maybe they could round trip things? E.g., use the model trained only on internal content to generate training data (which you could probably do some kind of screening to remove anything you don't want leaking) and then train a new model off just that?
I think the more interesting question here would be if someone could fine tune an open weight model to remove knowledge of a particular library (not sure how you'd do that, but maybe possible?) and then try to get it to produce a clean room implementation.
I don't think this would qualify as clean room (the Library was involved in learning to generate programs as a whole). However, it should be possible to remove the library from the OLMO training data and retrain it from scratch.
But what about training without having seen any human written program? Coul a model learn from randomly generated programs?
> I don't think this would qualify as clean room (the Library was involved in learning to generate programs as a whole)
Hm... I mean this is really one for the lawyers, but IMO you would likely successfully be able to argue that the marginal knowledge of general coding from a particular library is likely close to nil.
The hard part here imo would be convincingly arguing that you can wipe out knowledge of the library from the training set, whether through fine tuning or trying to exclude it from the dataset.
> But what about training without having seen any human written program? Coul a model learn from randomly generated programs?
I think the answer at this point is definitely no, but maybe someday. I think it's a more interesting question for art since it's more subjective, if we eventually get to a point where a machine can self-teach itself art from nothing... first of all how, but second of all it would be interesting to see the reaction from people opposed to AI art on the basis of it training off of artists.
Honestly given all I've seen models do, I wouldn't be too surprised if you could somehow distill a (very bad) image generation model off of just an LLM. In a sense this is the end goal of the pelican riding a bicycle (somewhat tongue in cheek), if the LLM can learn to draw anything with SVGs without ever getting visual inputs then it would be very interesting :)
We’re talking about agents here. (These are, after all, what MCP servers are meant to serve to.) Thus we’re talking about the need for services to be efficiently agent (computer) accessible, not efficiently end-user accessible.
reply