Yet another Hacker News

Opus 5.5 agents discover two room-temperature magnetic semiconductor candidates

148 points outlier99 2 hours ago 115 comments

Ygg2 2 hours ago | parent

Ugh. Unless this has been actually experimentally verified to be a room-temperature and room-pressure superconductor, it's about as ground breaking as "Yet another promising nuclear fusion candidate theoretically described."

ChickeNES 2 hours ago | parent

Well, given that this is a semiconductor, and not a superconductor, I don't see how that is relevant?

xmodem 2 hours ago | parent

Reading the title I saw the words "room-temperature" and my mind auto-completed it to superconductor, and based on other comments I don't think i'm alone in that.

Lerc 1 hour ago | parent

I agree that it is about as ground breaking as "Yet another promising nuclear fusion candidate theoretically described."

I'm not sure why you would consider new and promising avenues for research to not be ground breaking. If it's an idea worth trying, it's an idea worth trying. If it doesn't survive testing, then it was still worth trying.

vatsachak 2 hours ago | parent

I could have gotten this in one prompt lmao

rfgplk 2 hours ago | parent

This gave me the idea to actually create a full (QED accurate) atomic simulation software. Essentially would allow you to play around with things like this. At a glance my workstation _probably_ has enough compute to handle it. At least to fully simulate at least a few dozen atoms and compounds.

meindnoch 1 hour ago | parent

You should consider patenting this very much novel idea, my friend!

No worries, your workstation is more than enough to run accurate quantum simulations!

rfgplk 2 hours ago | parent

Current frontier LLMs empower effectively anyone with limitless knowledge. Historically, if I wanted to hire an engineer to, say, create something like this I would have needed a multi-million dollar budget. Now, anyone with $200 (or less) can achieve it.

devmor 2 hours ago | parent

You are vastly overestimating what has been achieved here.

This is something a couple of materials science grad students can do in limited time for poor compensation as well. The expensive budget is for the part that comes next.

rfgplk 2 hours ago | parent

Of course, "LLM solves quantum gravity and proves existence of God", "nah brah, that's easy brah any kid could have done this brah".

This is what you sound like. I also like how the goalposts keep moving on a daily basis, a year ago it was that LLMs can't even write a Hello World program without making an error, but now things like this are "so easy a minimum wage intern could do it."

suddenlybananas 2 hours ago | parent

It hasn't done that though.

devmor 1 hour ago | parent

Why hyperbolize when I am commenting on something it has actually done and the vastly exaggerated claims related to this?

SpicyLemonZest 1 hour ago | parent

Isn't there quite a bit of space between "so easy a minimum wage intern could do it" and your original claim that it would have cost millions of dollars to produce these results?

dev_l1x_be 2 hours ago | parent

I am not sure how this process looks like. When they "discover" these, what are they actually doing?

    The agents ran quantum-mechanical simulations of each crystal with the standard method for this, density functional theory, at two levels of approximation: a faster one (PBE+U) and a slower, usually more accurate one (HSE06). The band gaps and spin windows below come from the more accurate one.

So the agent runs a classic simulation or I am missing something.

rfgplk 1 hour ago | parent

Frankly, there is no point in trying to "understand" what an LLM does. Their thought process is effectively undecipherable by humans (it's essentially information arising from information) so even such a "simple explanation" is almost certainly wrong. The agents might appear to have "used this method", but the actual method of computation is far beyond our grasp.

Why are people being so belligerent about this? I thought it's fairly obvious at this point that LLM reasoning is far beyond anyones understanding. Or does anyone have a refutation?

amoorthy 1 hour ago | parent

Yes I saw 3Blue1Brown say the same thing in his tutorial on how neural nets worked where he built a simple model to recognize a particular letter. Good reminder.

rfgplk 1 hour ago | parent

I've been dabbling with some of my own (tiny) models recently and it's actually shocking at what they can "learn" despite having _zero_ mention of it in it's training data.

reasonableklout 1 hour ago | parent

This is a strange attitude. When an agent is optimizing a piece of code, comes up with 2 variations, and runs benchmarks on them to figure out which one is faster, then selects one of them based on tradeoffs between performance and other things it reasons about, do you ignore its explanation and all experiment runs?

static_motion 1 hour ago | parent

>Their thought process is effectively undecipherable by humans (it's essentially information arising from information

Are you trying to say that human brains are incapable of inference?

black_knight 1 hour ago | parent

What are you on about? I have had Fable come up with new shit for me several times (I do research for a living, so actual new shit nobody knew before), and each time it was perfectly understandable.

Of course I don’t know how it got its ideas for what to try. But heck, I don’t even understand how I get my ideas half the time. But the process, like what code it wrote, simulations it ran etc can be understood by (some) humans just fine!

fasterik 1 hour ago | parent

You're confusing the weights of a model and internal chain-of-thought with the output of the model. Yes, we don't know a lot about how the internal mechanisms work. But with the correct prompt, agents will produce a worklog that documents exactly what solutions were tried and how the result was obtained.

__MatrixMan__ 1 hour ago | parent

I'm under the impression that this kind of modeling is one of the applications that quantum computers are likely to be good at.

I'd imagine there's a lot of documented research which has attempted to find such things using classical computers.

Seems like there would be a lot of well structured context for somebody to use while directing agents to repeat that research, now with updated models once quantum computing is ready for that kind of task.

atq2119 1 hour ago | parent

A lot of the public successes with agents is really LLM-driven local search against an objective function that is evaluated in more traditional ways. This one seems to fit the pattern.

dekhn 1 hour ago | parent

not a classic simluation- a quantum simulation. This means they put a lot more work into representing the wave function of the simulation and modelling quantum effects.

contemporary343 1 hour ago | parent

They used quantum espresso.. undergrads usually run this in certain classes: https://www.quantum-espresso.org They didn't do any work there.

dekhn 1 hour ago | parent

You misunderstood what I said. I mean that quantum calcs are more computationally expensive than classical simulations ("more work"). I am not saying the authors of this blog did anything special.

contemporary343 1 hour ago | parent

They ran Quantum Espresso which is ok, but by no means the 'state of the art' for DFT. And in case, any DFT computation has to be taken with a few pounds of grains of salt before getting too excited about it.

No offense to the person writing this (assuming they did at all), but I'm not sure they really understand what they're doing..

rsfern 1 hour ago | parent

Modeling superconductivity with DFT is tricky, there are plenty of DFT reports from reputable groups explaining why LK-99 should be superconducting. It’s a limitation of the theory, DFT can’t model correlated electron states well, and it’s not great at finite temperature, and both of those are important for superconductivity.

scrlk 2 hours ago | parent

After the LK-99 debacle, I'm taking this with a truck load of salt.

zaep 1 hour ago | parent

I think, of course, skepticism around this "LLM discovers X" thing is warranted, and there have been plenty of more recent examples around questionable LLM "discoveries". Just stating this because the LK99 thing I believe was notable as a (supposed) room-temp _super_conductor while this is about a _semi_conductor.

post-it 1 hour ago | parent

Oh wait, you're right. I misread the title. Don't we already have room temperature semiconductors?

gus_massa 52 minutes ago | parent

Yep. This has interesting magnetic properties.

In magnetic materials, you must calculate separately the current with spin up and spin down and there ara meny interesting applications. My favorite is[1] https://en.wikipedia.org/wiki/Giant_magnetoresistance

[1] Was. Because it has used for hard disks (see the applications section). Now SSD ruins the interesting anecdote.

DanHulton 40 minutes ago | parent

Oh wow, I had the same misread and the same gut reaction.

mlmonkey 1 hour ago | parent

You probably meant "I'm taking this with a tiny pinch of salt". The amount of salt is directly proportional to how much of the claim you are willing to accept.

Edit: I stand corrected. According to Gemini:

Me: Does using more salt mean accepting more of that claim?

Gemini: No, it actually means the exact opposite. If you say you need to take a claim with a huge pile of salt (or a shovel of salt), it means you believe the claim is highly unbelievable and you need an immense amount of skepticism to accept it. How the Metaphor Scales

• A single grain of salt: "I am slightly skeptical, but it could be true."

• A pinch of salt: "I have a healthy amount of doubt about this."

• A grain of sand / A truckload of salt: "This sounds completely made up, and I barely believe a single word of it."

The salt represents your skepticism, not your belief. Therefore, the more unbelievable the claim, the more "salt" you need to swallow it.

tempestn 1 hour ago | parent

Citation needed.

ReptileMan 1 hour ago | parent

Inversely proportional

Retro_Dev 1 hour ago | parent

Hmm? I always thought it was how much you had to flavor the statement to swallow it.

frereubu 1 hour ago | parent

I don't think this is right. https://en.wikipedia.org/wiki/A_grain_of_salt The "grain" isn't a single grain, it's an old English measure which is around 65mg, i.e. roughly how much there is in a pinch. I've also only ever heard people use larger amounts to mean more scepticism.

PostOnce 1 hour ago | parent

A person leans on the titanic intellect of a trillion dollar company's most fearsome LLM, only to be corrected by a random commenter with a link to Wikipedia.

We live in interesting times.

esperent 1 hour ago | parent

No, the implementation is that something "tastes off" so you need to add a pinch (+) of salt to make it palatable. The more off it tastes, the more salt you need.

(+) Or a "grain" if you're from the US since American English sayings seem to all date from the middle ages, while the rest of the English speaking world tends to update ours over time. No shade meant, I've just always found that interesting.

plastic-enjoyer 1 hour ago | parent

I guess mlmonkey is a fitting name.

adriand 1 hour ago | parent

> After the LK-99 debacle

"Debacle"? That was the most fun I've had on the Internet in years. When's the last time so many people engaged in so many arguments about materials science and electromagnetism? Sometime in the 1800s?

ntonozzi 1 hour ago | parent

Maybe he meant 'debacle' in an endearing sense, not a derogatory one. I personally agree with you and loved this debacle.

gekoxyz 1 hour ago | parent

Yeah I remember going to my physics professor super excited about LK-99 to ask him if he heard about it, and him just telling me "yes but stuff like that happens twice per year, they will find something is off", and in fact it's what happened...

mawadev 1 hour ago | parent

I start my day with plenty of optimism, then I go back and forth in the CLI and find out most of whats posted online is fake, and then towards the end of the day 2h past my bed time I end up ed zitron maxxing, it is the way it is ig

jghn 58 minutes ago | parent

Even without the LK-99 debacle, I am *way* less excited about this than I was the original LK-99 announcement. The chance that this is real is close to 0%

AndrewKemendo 40 minutes ago | parent

I’m not sure what you mean by debacle

That was one of the best examples of science working nearly perfectly. One of the rare times I felt ok being human

to11mtm 21 minutes ago | parent

I think it did play out fairly as far as actual 'scientific method' goes.

I think as far as the 'debacle', there was definitely a lot of hype (at least as far as HN goes) around it, the level of buzz felt similar to what one would see today around a new AI model release.

fnord77 21 minutes ago | parent

this isn't about supercondutors, though

xgulfie 2 hours ago | parent

Anyone remember LK99 lol

zamadatix 1 hour ago | parent

That was a room temperature superconductor, a bit different of a task.

frereubu 1 hour ago | parent

This is semiconductors, not superconductors.

Legend2440 2 hours ago | parent

Interesting; but until actually made and tested, not worth getting excited over.

devmor 1 hour ago | parent

One of the materials is most likely impossible to synthesize. The other already exists, so that may actually be capable of being tested. It's only been synthesized once, 27 years ago though.

nrmitchi 1 hour ago | parent

> One of the materials is most likely impossible to synthesize

Is this a "actual impossible because it's inherently contradictory", or "we just don't know how to do it yet but give us a year"?

Legend2440 1 hour ago | parent

We don't know a way to precisely place atoms in a checkerboard pattern like that, without getting it so hot that the arrangement is destroyed.

It maybe could be possible but beyond the reach of current material science.

nrmitchi 1 hour ago | parent

I personally thinks that’s the more optimistic of the two options; I’ll take it as a win for today

devmor 1 hour ago | parent

"Likely Impossible" as in, we would need a revolutionary discovery in how thermodynamics apply to crystal formation.

postepowanieadm 2 hours ago | parent

Discovered in whose data?

hbn 1 hour ago | parent

All research is built off the existing body of all research data done by other people

einpoklum 1 hour ago | parent

I would image it's the data the researchers fed the agents and in which a discovery was likely. Especially since it's "candidates", so it's not like a proper discovery.

matthova 1 hour ago | parent

Sounds interesting. Excited to see physical versions of this cooked up. Also, very excited for a world a few years from now where we can talk about accomplishments like this from the frame of the driver of the AI, rather than hype that AI helped.

colijobles 1 hour ago | parent

While we should be skeptical until made in a lab or verified by others, this is a much better use of LLMs than solving math theorems/conjectures

nrmitchi 1 hour ago | parent

This is frankly one of the best uses of LLMs (along with proposing and evaluating drug therapies), and I think it's (at least partially) because these are things that will only work in the hands of people who are already experts and motivated in the field. The proposed thing is validate (or not validated), and then everyone moves on (either using the cool new thing, or knowing that it doesn't work). I'd also throw robotics in here.

The fact that the major "uses" of LLMs have been contributing to the acceleration of the dead internet theory, and building millions of versions of the same apps that no one is going to maintain, is extremely sad.

jonplackett 1 hour ago | parent

A lot of these ‘an agent invented’ or ‘an agent solved’ are actually the agent wading through a lot of info and finding something a human did that no one noticed or saw the relevance of at the time.

If ai becomes so prolific that we humans all stop doing those things then will they still work?

Schiendelman 1 hour ago | parent

Yes, as long as we are advancing to behavior and world models, so that agents can interact with the world themselves. Which we are.

chris_money202 1 hour ago | parent

Well its not just any old human doing these things in a general sense. Its typically academics or highly paid researchers who love doing work like this. So, I don't think it will just one day stop

jonplackett 1 hour ago | parent

I think access to AI too early (before any expertise) is going to serious cripple educational development.

Next gen of scientists might look quite different.

chris_money202 1 hour ago | parent

That is probably true, but the ones that make it through to become experts might get super-charged with AI as well

jonplackett 43 minutes ago | parent

But my ponderance is - is that enough. Is AI supercharging or just super finding?

gabbagool 1 hour ago | parent

Which is somewhat ironic since neural networks were "discovered" back in the 1940s... then forgotten... then wait, they were discovered again! ... then forgotten, again... and now here we are.

thinkcontext 40 minutes ago | parent

We didn't have big enough compute and data to do interesting things with them until recently. That changed with ImageNet in 2012

https://www.technologyreview.com/2020/11/03/1011616/ai-godfa...

nico 1 hour ago | parent

In a way, you can think of pretty much anything we express with language, especially things that are already modeled in scientific language, or logical language, or in equations or code; to be representable in a parametric/searchable space

Thus, you can build ai/ml models+agents to explore those spaces, at a speed and scope much larger than what any human can do

I can imagine findings like these are going to keep increasing in frequency to a point in which the bar for novelty goes a lot higher

esafak 1 hour ago | parent

It is not at all obvious that merely because we have words for concepts, that a model should be able to do all these miraculous mathematical and scientific things.

jeremyjh 1 hour ago | parent

Right, it also has to model a substantial fraction of reality (or at least a true simulation of it) to accomplish these things.

SR2Z 1 hour ago | parent

It models our language, which is a flawed and imperfect way of describing the world. So far, it seems like a lot of these discoveries are "filling in the gaps" between the things we've written down and the things they imply (if you have the memory to think them through).

The story about OpenAI's Navier-Stokes solution is a good example of what I mean. I don't think it would have been possible without computer assistance because that proof is long and complicated. I'm also not sure that it would have been possible without a human proposing a new approach to the problem, because by all accounts that's exactly what led to the absurd amount of spending that OpenAI did to solve the issue.

I feel like that at least implies that there's some room left for humans in the new world.

nico 1 hour ago | parent

You are correct. My comment is not so much about that this is something elementary. But rather an observation that, given the current state of technology, it seems like we are being able to model increasingly more things, in increasingly more efficient and automated ways, to the point that there seems to be a pattern to it

nico 1 hour ago | parent

Anecdata: over the weekend, on a whim, I decided to download a real fly’s brain’s weights [0], run it on a simulated task like finding food, then train a logistic classifier using the fly’s decisions as the expert, then use the trained classifier as a decision model to simulate the fly on a 3d environment, running in real time on a website

It took me (using Claude code and some codex), about 3 hours to put it together

And even though it was a cool demo, it seemed so easy, that it also felt like it wasn’t worth sharing

0: ChessFly (not mine), uses the FlyWire connectome (the fly’s brain’s weights) to play chess https://huggingface.co/spaces/mlabonne/chessfly

polishdude20 1 hour ago | parent

Oh please do share!

nico 1 hour ago | parent

https://playground.jeffyclassify.com/#fly

It's a small machine, so it might get bogged down

binsquare 1 hour ago | parent

I think ai certainly raises the bar for those with taste

tripleee 1 hour ago | parent

Many people wouldn't find that easy, even with AI

chneu 35 minutes ago | parent

This can be said about anything.

caaqil 19 minutes ago | parent

> This can be said about anything.

More generally, anything can be said about anything.

nater5000 1 hour ago | parent

Yeah...?

That's the pitch of LLMs lol

randbyte 1 hour ago | parent

Who is vals.ai and why they keep submitting eye-catching claims. A few weeks ago they said fable 5.1 solved some obscure cipher and now opus 5.5 found room temperature semiconductor candidates. Meanwhile they seem to be in the business of making benchmarks.

Are they a promoter / influencer for Anthropic?

contemporary343 1 hour ago | parent

It's an evals platform. The problem is to promote evals in scientific domains you need to actually know something about them. Otherwise you end up with slop like this.

einpoklum 1 hour ago | parent

This should probably read: "Researchers discover two room-temperature magnetic semiconductor candidates. They used Opus 5.5 agents to perform some checks."

tedsanders 1 hour ago | parent

> We’re all used to two types of magnet. The common one, the fridge magnet, is ferromagnetic — its atomic magnets all point the same way (up or down), adding their magnetic effects. The less well known one, the antiferromagnet (AF), has neighbouring atomic magnets that point opposite ways and exactly cancel out magnetically.

This is a very bizarre introduction. People encounter diamagnets (e.g., copper) and paramagnets (e.g., aluminum) way more than they encounter antiferromagnets. I don't know why you'd ever cast magnetism as a false binary between ferromagnets and antiferromagnets, without acknowledging any other types of magnetic order.

(I did a PhD in magnetic materials)

Edit: I'll add that whether an antiferromagnet is useful, say, for exchange biasing a ferromagnetic thin film, depends on many factors. Just looking at antiferromagnetism alone you've got collinear vs non-collinear, G-type vs A-type vs C-type, commensurate vs incommensurate, and isotropic vs anisotropic; and all of that interacts with the interface structure, yada yada yada. It would be helpful if the authors elaborated on the expected properties of these materials. I personally don't know what people want room-temperature magnetic semiconductors for, but I'd be curious to learn what set of properties they think would be useful.

comradesmith 1 hour ago | parent

I also like how they explained ferromagnetism as being arranged atomic magnets. Magnets all the way down.

tedsanders 1 hour ago | parent

Yeah, and it's not even an accurate explanation either.

> The common one, the fridge magnet, is ferromagnetic — its atomic magnets all point the same way (up or down), adding their magnetic effects.

Ferromagnets typically have domains with magnetic moments that point in different directions. Ferromagnets can have a net magnetic moment without every 'atomic magnet' pointing the same way.

https://en.wikipedia.org/wiki/Magnetic_domain

Refrigerator magnets in particular are usually magnetized as Halbach arrays, where the whole point is that the 'atomic magnets' are not pointing in the same direction. This is more energetically stable, which allows you to use cheaper materials.

https://en.wikipedia.org/wiki/Refrigerator_magnet

Lastly, I believe most refrigerator magnets are actually ferrimagnetic, not ferromagnetic. (The distinction doesn't matter much for users of magnets, but is important for the materials scientists studying and designing them.)

https://en.wikipedia.org/wiki/Ferrimagnetism

contemporary343 1 hour ago | parent

This is what happens when Claude writes it for you (and you don't review it)

aero142 1 hour ago | parent

So, Claude claims a new discovery and then someone else's Claude writes the blog posts. It would be helpful if I could get Claude to read this for me and post dejected HN comments in response.

post-it 1 hour ago | parent

You can! And I believe many do. But please don't.

EA-3167 1 hour ago | parent

It's not perfect by any means, but Pangram indicates 100% human written. Remember people can be quite foolish without any machine assistance.

joshuat 49 minutes ago | parent

Never thought about how much it must suck to be an engineer named Claude right now

bryanlarsen 47 minutes ago | parent

Not as much as being a woman named Karen.

reilly3000 30 minutes ago | parent

Or Siri. I knew one who was deeply upset about the whole thing.

sgarland 12 minutes ago | parent

I am deeply upset every time the HomePod in another room decides to attempt to answer my query instead of the phone that’s in my hands, which then has to ask who is speaking, and has a 50:50 chance of ultimately failing to do the task.

With how magical handoff / continuity / whatever it’s called is, it is baffling to me why Apple allows the HomePod to so aggressively take over requests when it sucks so, so much at it.

ggm 10 minutes ago | parent

Siri, Claude and Karen walk into a bar. Nobody serves them because the robots.txt forbade it.

lifeisloving 1 hour ago | parent

The people who wrote this seem to be lacking in expertise, and its just a model benchmarking company..Whos every article is just hyperbole about llms.

Not sure why we're calling it a discovery, when they've literally been made before, by a human.

otterley 1 hour ago | parent

I wouldn't describe them both as being newly-discovered. The second one, KV[Cr(CN)₆], had already been discovered.

malfist 1 hour ago | parent

Okay? Aren't the semiconductors we use today room temperature? I certainly don't use helium to cool my phone.

I don't see any claims that this is better than the current silicon and gallium arsenide semiconductors that we use. And the use of "room temperature" seems a deliberate attempt to misconstrue this with superconductors

drdeca 54 minutes ago | parent

1) the “room temperature” bit did cause me to initially misread it in the way you describe, so you may be right about that.

2) it is specifically saying it is a magnetic semiconductor. The Wikipedia article on the topic says “ To date, GaMnAs remains the only semiconductor material with robust coexistence of ferromagnetism persisting up to rather high Curie temperatures around 100–200 K.” , so this would be something new. (The silicon chips in your smartphone are not ferromagnetic.)

maipen 52 minutes ago | parent

Any sort of alternative discovery, even though it may be inferior, is a great achievement made by AI; Meaning that better discoveries are possible too.

monocasa 1 hour ago | parent

Sounds like a good reason to hire a lab to make some, and then make a big deal about it if the results pan out.

I can think of worse uses of VC AI funding.

okamiueru 52 minutes ago | parent

Gotta pump it as much as possible before the IPO.

poulpy123 1 hour ago | parent

Lmao, anything goes

contemporary343 1 hour ago | parent

Finding some new combination or iteration in the literature and running DFT is the kind of thing a senior undergraduate or first year grad student typically does (and typically with Claude anyway these days). (And yes, they'd probably use Quantum Espresso to start, like this writeup and its agent does). They'd probably show it at a weekly lab meeting where it would get ripped apart. And they would not be blasting a preliminary calculation around the world as if they'd made a new discovery.. but hey, we're in a brave new world; maybe they should!

esperent 1 hour ago | parent

The title has been editorialized.

Actual title:

Two Room-Temperature Antiferromagnetic Semiconductor Candidates

There's nothing unusual about finding room temperature semiconductors. I assume whoever posted it misread this as room temperature superconductors, but it has nothing to do with that.

What's interesting here is the antiferromagnetic part of the title, which was removed. I think this makes it relevant for e.g. RAM, but not superconducting. Someone can correct me if I'm wrong.

WesBrownSQL 1 hour ago | parent

I've got a friend who has been doing this research since the 90s. There is real money involved in this. This isn't like a math proof with a 1mm dollar payout. I seriously doubt this discovery. Until they show it working, I call bullshit. A room-temperature semiconductor is worth WAY more than an AI company.

pbrumm 41 minutes ago | parent

If they are confident in their discovery they should pay some scientists to start making this and testing it out.

ariwilson 19 minutes ago | parent

vals.ai has great marketing! Unclear if the product is great yet. Or what it is exactly.