This is the kind of thing I like to see AI being used for. That said, as is noted in the article, this has not yet led to new physics or any indication of new physics.
not an LLM, in case you're wondering. From the PyTheus paper:
> Starting from a dense or fully connected graph, PyTheus uses gradient descent combined with topological optimization to find minimal graphs corresponding to some target quantum experiment
The AI rediscovered an interferometer technique the Russian's found decades ago, optimized a graph in an unusual way and came up with a formula to better fit a dark matter plot.
> Initially, the AI’s designs seemed outlandish. “The outputs that the thing was giving us were really not comprehensible by people,” Adhikari said. “They were too complicated, and they looked like alien things or AI things. Just nothing that a human being would make, because it had no sense of symmetry, beauty, anything. It was just a mess.”
This description reminds me of NASA’s evolved antennae from a couple of decades ago. It was created by genetic algorithms:
What’s amazing to me is this design looks a hella lot like tree branch formations to me. Makes me wonder if trees have some form of antenna-like functionality we are unaware of.
Referring to this type of optimization program just as “AI” in an age where nearly everyone will misinterpret that to mean “transformer-based language model” seems really sloppy
"It added an additional three-kilometer-long ring between the main interferometer and the detector to circulate the light before it exited the interferometer’s arms."
Isn't that a delay line? The benefit being that when the undelayed and delayed signals are mixed, the phase shift you're looking for is amplified.
Am I understanding the article correctly that the created a quantum playground, and then set thein algorithm to work optimizing the design within the playgrounds' constranits? That's pretty cool, especially for doing graph optimization. I'd be curious to know how compute intensive it was.
The "AI" here is not the same "AI" as claude, Grok or OpenAI. It's just an optimization algorithm that tries different things in parallel until it finds a better solution to inform the next round.
Impressive results, I remember reading about AI-generated microstrip RF filters not too long ago, and someone already mentioned evolved antenna systems. We are suffering from a severe case of calling gradient descent AI at the moment, but if it gets more money into actual research instead of LLM slop, I'm all for it.
This AI-designed experiment is pretty cool. It seemed kind of weird at first, but since it actually works, it’s worth paying attention to. AI feels more like a powerful tool that helps us think outside the box and come up with fresh ideas. Is AI more of a helper or a creator when it comes to research?
Article mentions that if students present these designs, they’d be dismissed as ridiculously. But when AI present them, they’re taken seriously.
I wonder how many times these designes were dismissed because humans who think out of the box too much are dismissed. It seems that students are encouraged NOT to do so, severely limiting how far out they can explore.
"it had no sense of symmetry, beauty, anything. It was just a mess."
Reminds me of the square packing problem, with the absurdly looking solution for packing the 17 squares.
It also reminds me of edge cases in software engineering. When I let an LLM write code, I'm often confused how it starts out, thinking, I would have done it more elegantly. However, I quickly notice, that the AI handled a few edge cases I only would habe caught in testing.
These days, it feels like “AI” basically just means neural network-based models—especially large autoregressive ones. Even convolutional neural networks probably don’t count as “real AI” anymore in most people’s eyes. Funny how things change. Not long ago, search algorithms like A* were considered the cutting edge of AI.
The article is misleading and badly written. None of the mentioned works seem to have used language or knowledge based models.
It looks like all the results were driven by optimization algorithms, and yet the writing describes AI 'using' concepts and "tricks". This type of language is entirely inappropriate and misleading when describing these more classical (if advanced) optimization algorithms.
Looking at the paper in the first example, they used an advanced gradient descent based optimization algorithm, yet the article describes "that the AI was probably using some esoteric theoretical principles that Russian physicists had identified decades ago to reduce quantum mechanical noise."
Ridiculous, and highly misleading. There is no conceptual manipulation or intuition being used by the AI algorithm! It's an optimization algorithm searching a human coded space using a human coded simulator.
Not-so-many years ago, this kind of work developing optimization algorithms would have been called optimization algorithms, not AI.
> We develop Urania, a highly parallelized hybrid local-global optimization algorithm, sketched in Fig. 2(a). It starts from a pool of thousands of initial conditions of the UIFO, which are either entirely random initializations or augmented with solutions from different frequency ranges. Urania starts 1000 parallel local optimizations that minimize the objective function using an adapted version of the Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm. BFGS is a highly efficient gradient-descent optimizer that approximates the inverse Hessian matrix. For each local optimization, Urania chooses a target from the pool according to a Boltzmann distribution, which weights better-performing setups in the pool higher and adds a small noise to escape local minima.
>they gave the AI all the components and devices that could be mixed and matched to construct an arbitrarily complicated interferometer. The AI started off unconstrained. It could design a detector that spanned hundreds of kilometers and had thousands of elements, such as lenses, mirrors and lasers.
22 comments
[ 1.8 ms ] story [ 42.1 ms ] thread"AI comes up with bizarre ___________________, but it works!"
> Starting from a dense or fully connected graph, PyTheus uses gradient descent combined with topological optimization to find minimal graphs corresponding to some target quantum experiment
The AI rediscovered an interferometer technique the Russian's found decades ago, optimized a graph in an unusual way and came up with a formula to better fit a dark matter plot.
There are a few things like that where we can throw AI at a problem is generating something better, even if we don't know why exactly it's better yet.
This description reminds me of NASA’s evolved antennae from a couple of decades ago. It was created by genetic algorithms:
https://en.wikipedia.org/wiki/Evolved_antenna
Isn't that a delay line? The benefit being that when the undelayed and delayed signals are mixed, the phase shift you're looking for is amplified.
I wonder how many times these designes were dismissed because humans who think out of the box too much are dismissed. It seems that students are encouraged NOT to do so, severely limiting how far out they can explore.
Reminds me of the square packing problem, with the absurdly looking solution for packing the 17 squares.
It also reminds me of edge cases in software engineering. When I let an LLM write code, I'm often confused how it starts out, thinking, I would have done it more elegantly. However, I quickly notice, that the AI handled a few edge cases I only would habe caught in testing.
Guess, we should take a hint!
It looks like all the results were driven by optimization algorithms, and yet the writing describes AI 'using' concepts and "tricks". This type of language is entirely inappropriate and misleading when describing these more classical (if advanced) optimization algorithms.
Looking at the paper in the first example, they used an advanced gradient descent based optimization algorithm, yet the article describes "that the AI was probably using some esoteric theoretical principles that Russian physicists had identified decades ago to reduce quantum mechanical noise."
Ridiculous, and highly misleading. There is no conceptual manipulation or intuition being used by the AI algorithm! It's an optimization algorithm searching a human coded space using a human coded simulator.
> We develop Urania, a highly parallelized hybrid local-global optimization algorithm, sketched in Fig. 2(a). It starts from a pool of thousands of initial conditions of the UIFO, which are either entirely random initializations or augmented with solutions from different frequency ranges. Urania starts 1000 parallel local optimizations that minimize the objective function using an adapted version of the Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm. BFGS is a highly efficient gradient-descent optimizer that approximates the inverse Hessian matrix. For each local optimization, Urania chooses a target from the pool according to a Boltzmann distribution, which weights better-performing setups in the pool higher and adds a small noise to escape local minima.
https://journals.aps.org/prx/abstract/10.1103/PhysRevX.15.02...
sounds kinda like the chip designer AI